Image Processing
R. Külcü; A. Süslü
Abstract
The Soil and Plant Analysis Development (SPAD) value is a significant parameter indicating chlorophyll content, particularly in the green parts of plants. Conventional SPAD meters determine this value by measuring the transmission and absorption of red and infrared radiation at a single point (2×3 ...
Read More
The Soil and Plant Analysis Development (SPAD) value is a significant parameter indicating chlorophyll content, particularly in the green parts of plants. Conventional SPAD meters determine this value by measuring the transmission and absorption of red and infrared radiation at a single point (2×3 mm2 sensor size). However, obtaining a comprehensive value for an entire leaf requires multiple measurements, increasing processing time. In this study, a non-destructive method for predicting SPAD values was developed using image processing techniques to determine dominant wavelength values from leaf photographs. A custom-designed photo box with controlled 6000 lux white LED lighting was used to capture images at a fixed distance of 15 cm. Images were processed using Color Picker (2024) software, where green components of the leaf were analyzed to extract dominant wavelength values. The results demonstrated that SPAD values could be accurately predicted using dominant wavelength data, with a 98.33% accuracy for the linear model (RMSE: 1.308) and 98.43% for the polynomial model (RMSE: 5.467). The findings indicate that a linear model provides a more precise correlation. This novel approach enhances the efficiency of SPAD measurement and offers a rapid, non-destructive alternative to conventional methods.
Image Processing
M. Keerthivasan; S. Kokilavani; M. Shanthi; Ga. Dheebakaran; R. Pangayar Selvi; M. Murugan; T. Elaiyabharathi; P. S. Shanmugam; M. Selva Kumar
Abstract
Influence of a single atmospheric component or meteorological variable on the host, pathogen, or their interaction in controlled environments has accounted for the majority of climate change’s impact on plant pests and diseases. Climate change can lead to alterations in the stages and rates of ...
Read More
Influence of a single atmospheric component or meteorological variable on the host, pathogen, or their interaction in controlled environments has accounted for the majority of climate change’s impact on plant pests and diseases. Climate change can lead to alterations in the stages and rates of growth of pests and diseases, host resistance, and the physiology of host-pathogen or host-pest interactions, which can cause substantial harm and reduce tomato crop yields. Different approaches have been ineffective in the accuracy of pest and disease forewarning in past years. The remarkable progress in Deep Convolutional Neural Networks (DCNNs) is revolutionizing the early detection of pests and diseases in crops. By analysing vast amounts of present and historical climate data, alongside their expertise in object identification and image categorization, these AI models can predict outbreaks with impressive accuracy. However, understanding the specific microclimate suitable for each pest and disease is crucial for truly effective intervention. Combining these two elements creates a powerful, targeted approach to preserving crops. A forewarning system can help to reduce the use of pesticides, thereby reducing the cost of production and environmental pollution. Proper cloud servers and IoT-based sensor networks should be used for a better forewarning of pests and diseases in future circumstances.
Image Processing
A. Soleimanipour
Abstract
IntroductionThe increasing demand for automation in agriculture, particularly for repetitive and labor-intensive tasks, has driven the development of robotic harvesting systems. Recent advances in computer vision, deep learning, and the availability of large image datasets have made it possible to create ...
Read More
IntroductionThe increasing demand for automation in agriculture, particularly for repetitive and labor-intensive tasks, has driven the development of robotic harvesting systems. Recent advances in computer vision, deep learning, and the availability of large image datasets have made it possible to create robust object detection models for agricultural applications. Traditional harvesting methods, such as bulk harvesting, often lead to fruit damage and loss owing to non-selective picking. Selective harvesting, particularly with the use of robotic systems, offers a promising alternative by combining the precision of human labor with the efficiency of automation. This study presents a deep learning-based model for detecting cucumber fruits on plants in a real greenhouse environment, which is an essential step towards developing autonomous harvesting robots that selectively pick ripe cucumbers.Materials and MethodsA dedicated image dataset was curated in a commercial greenhouse, comprising 300 images of cucumber plants captured under various lighting conditions (morning, noon, and evening), to ensure robustness against real-world variability. Images were manually labeled to identify the cucumber fruits and their pedicels. To enhance the model training and prevent overfitting, data augmentation techniques were applied to the training set. Several architectures of the YOLO (You Only Look Once) object detection algorithm were evaluated, including the nano-scale versions YOLOv5n and YOLOv8n, and the small-scale YOLOv8s, in addition to the RT-DETR model.The YOLOv8 algorithm is known as one of the state-of-the-art algorithms in computer vision because of its high speed, detection accuracy, and adaptability. The YOLOv8 architecture consists of three main parts: backbone, neck, and head, which are responsible for extracting image features, combining and enriching features, and predicting bounding boxes and object classes, respectively.These models were trained, and their performances were compared based on the detection accuracy and inference time metrics. Training and evaluation were conducted using a suitable computational platform.Results and DiscussionThe performances of different YOLO models and RT-DETR were rigorously evaluated. The results demonstrated that the YOLOv8n model achieved the highest detection accuracy of 87.5%, surpassing the performances of the other tested models. Importantly, the YOLOv8n model also exhibited a favorable balance between the accuracy and inference time, making it suitable for real-time applications. The analysis considered the trade-off between the number of parameters and detection speed, highlighting the efficiency of YOLOv8n.The YOLOv8n model demonstrated superior performance in terms of pedicel detection accuracy compared to YOLOv5n, achieving a fitness score of 91.08% (calculated as a weighted average of mAP@50 and mAP@50-95). While exhibiting strong performance in fruit and pedicel detection (Figure 6), the sensitivity of the model for pedicel detection (88.0%) was comparatively lower than that for fruit detection (96.1%). The highest F1 score (0.89) was observed at a confidence level of 39.5%, indicating the effectiveness of the model in balancing the precision and recall for pedicel detection. Overall, YOLOv8n outperformed the other tested models in identifying the class and location of the fruit pedicel. The superior performance of YOLOv8n can be attributed to its architectural advancements and optimized training processes.ConclusionThis study successfully developed a deep learning-based model for accurate and efficient cucumber fruit detection in a greenhouse environment. The YOLOv8n model demonstrated superior performance compared with the other evaluated architectures, achieving a detection accuracy of 87.5% while maintaining a good processing speed. These findings suggest that the YOLOv8n model has significant potential for integration into autonomous vegetable harvesting robots, contributing to the automation of agricultural processes and increased efficiency in greenhouse operations. Future works should explore further optimization and testing under diverse environmental conditions.
Image Processing
M. Najafabadiha; D. Mohammad Zamani; M. Gholami Par-Shokohi
Abstract
This study proposes a novel method for identifying grape leaf diseases through RGB image analysis combined with weighted group decision-making. The investigation focused on five disease types, Black Measles, Black Rot, Leaf Blight, Powdery Mildew, and Downy Mildew, along with healthy leaves. Three machine ...
Read More
This study proposes a novel method for identifying grape leaf diseases through RGB image analysis combined with weighted group decision-making. The investigation focused on five disease types, Black Measles, Black Rot, Leaf Blight, Powdery Mildew, and Downy Mildew, along with healthy leaves. Three machine learning classifiers, namely support vector machine (SVM), random forest (RF), and k-nearest neighbor (k-NN), were employed individually and in a weighted ensemble. Each classifier was assigned a weight based on its accuracy, and the final disease classification was determined using a majority voting strategy. To determine the most discriminative features related to texture, color, and shape, the Relief feature selection algorithm was applied, which identified the top five effective features in diagnosing grape leaf diseases. Experimental results indicated that the classification accuracies of SVM, RF, and k-NN were 88.33%, 80.08%, and 75%, respectively. Furthermore, the proposed weighted group decision-making approach improved the overall classification performance, achieving an accuracy of 91.67%.
Image Processing
M. H. Nargesi; K. Kheiralipour; F. Valizadeh Kakhki; Z. Moradi
Abstract
IntroductionPaying attention to the technical aspects of production plays a crucial role in increasing yield and ensuring sustainable agriculture. Organic fertilizers, such as poultry manure, contribute to plant growth by providing essential nutrients and improving soil quality. However, they alone cannot ...
Read More
IntroductionPaying attention to the technical aspects of production plays a crucial role in increasing yield and ensuring sustainable agriculture. Organic fertilizers, such as poultry manure, contribute to plant growth by providing essential nutrients and improving soil quality. However, they alone cannot fully meet the nutritional needs of plants. The combination of organic and chemical fertilizers is an effective approach to enhancing soil fertility and boosting crop performance, ultimately leading to sustainable agricultural development. Integrated nutrient management also helps reduce the use of chemical fertilizers while minimizing their harmful effects on the environment. Potassium is an essential element in plant nutrition, playing a key role in processes such as photosynthesis, growth, chlorophyll production, and transpiration regulation. Additionally, under stress conditions, potassium enhances water uptake and regulates osmotic pressure, helping to maintain plant health. Potassium fertilizers are classified into two categories: chloride-based and chloride-free. Potassium sulfate, due to its lack of chloride, is a suitable option for chloride-sensitive crops such as tea, potatoes, and sugar beets. Meanwhile, hyperspectral imaging has emerged as an innovative technique with broad applications in detecting chemical parameters, assessing quality, and analyzing the purity of agricultural and food products. This study utilizes hyperspectral image processing technology to determine the pH level of potassium sulfate.Materials and MethodsThe present study was conducted in the Image Processing Laboratory at the Ilam University, Iran. To determine the pH level of potassium sulfate, four different levels of 2.5, 2.6, 2.8, and 2.9 were considered. The pH measurement was performed in the laboratory using a flame photometer. The required images were obtained through hyperspectral imaging using the line-scan method. For each pH level, three samples were obtained and six hyperspectral images were captured for each sample, resulting in 18 images per pH level and a total of 72 hyperspectral images for each pH level. MATLAB software was used for the analysis and processing of these images. The image processing stage included wavelength selection, feature extraction, and feature selection. Finally, the selected features were classified using an artificial neural network.Results and DiscussionPrincipal Component Analysis performed on the hyperspectral image channels of potassium sulfate revealed significant variations in the principal component values across different pH levels. This finding indicates that pH conditions exert a considerable influence on the spectral response of the samples. Based on the prominent peaks obtained from the analysis, the most relevant channels were identified, and their corresponding wavelengths were determined as the optimal spectral bands. The selected channels for the four pH levels were 65, 327, 334, 482, 510, 607, and 644, with their corresponding effective wavelengths being 453.32, 669.95, 675.74, 798.11, 821.26, 901.47, and 932.06 nm, respectively. To extract discriminative spectral information, six features were computed from each of the selected wavelengths. Consequently, a total of 42 features were obtained, which were subsequently employed in the classification process of different pH levels. The confusion matrices of the classification model based on the artificial neural network were obtained to evaluate the model's accuracy. The classification accuracy for detecting the pH level of potassium sulfate was 98.6% with effective features and 97.2% without them.ConclusionThe results of this study demonstrated the high potential of hyperspectral imaging technology combined with the artificial neural network classification method, using strategies with and without effective feature selection, in detecting the pH level of potassium sulfate. The proposed method offers several advantages over laboratory-based approaches, such as being non-destructive, having high speed, and being cost-effective. It is suggested to explore other methods for classifying hyperspectral images for determining the pH level of potassium sulfate. The proposed method in this study could also be applied in the future to identify various chemical elements in potassium sulfate.
Image Processing
M. Latifi-Amoghin; Y. Abbaspour-Gilandeh
Abstract
IntroductionTraditional methods for evaluating fruit quality, such as pH measurement, are often destructive, time-consuming, and costly, leading to product loss and reduced efficiency in the supply chain. The growing need for rapid, accurate, and non-destructive methods makes the use of technologies ...
Read More
IntroductionTraditional methods for evaluating fruit quality, such as pH measurement, are often destructive, time-consuming, and costly, leading to product loss and reduced efficiency in the supply chain. The growing need for rapid, accurate, and non-destructive methods makes the use of technologies like Hyperspectral Imaging (HSI) essential. HSI combines two-dimensional imaging with spectroscopy to simultaneously acquire spatial and spectral information from an object. Numerous studies have shown that this method is capable of accurately estimating internal fruit parameters in a non-destructive manner. The objective of this research was to develop a fast and reliable method for the non-destructive estimation of pH in two plum cultivars using HSI and machine learning algorithms such as Partial Least Squares Regression (PLSR) and Artificial Neural Networks (ANN). This study aims to overcome the limitations of conventional methods by leveraging the power of advanced imaging and computational techniques, providing a sustainable and efficient solution for the fruit industry.Materials and MethodsIn this study, 80 samples from each of the Khormaei and Khoni plum cultivars were used, which were purchased from local orchards. The samples were uniform in size, shape, and colour and were free from any physical damage. Hyperspectral images of the samples were acquired using a rotating hyperspectral imaging system in the range of 418 to 1072 nm. The pH of each fruit juice sample was measured using a digital pH meter. In the analysis of spectral data, the initial part of the spectrum was first removed due to high noise, and then the remaining data were processed with preprocessing methods such as a Gaussian filter and Multiplicative Scatter Correction (MSC). To select effective wavelengths (EWs), a hybrid approach using a Decision Tree (DT) and five metaheuristic algorithms was employed, with the Particle Swarm Optimisation (PSO) algorithm showing the best performance. Finally, pH modelling was performed on the selected wavelengths using PLSR and ANN. This comprehensive methodology ensures that the models are trained on high-quality data and are optimised for maximum accuracy.Results and DiscussionSpectral analysis showed that the reflectance spectra of the Khoni and Khormaei plums had a high degree of variation, which is related to the differences in their chemical composition and structure. Descriptive statistics indicated that the average pH of Khormaei plum (3.909) was higher than that of Khoni plum (3.7375), and the pH range of Khoni plum (3.15 to 4.44) was wider than that of Khormaei plum (3.6 to 4.2). The results showed that modelling with ANN on the wavelengths selected by PSO, especially for Khoni plum, significantly increased prediction accuracy. The best ANN model for Khoni plum achieved an R2 of 0.9834 and an RPD of 8.01, which indicates the outstanding accuracy of this method. For the Khormaei plum, the best ANN model also reached an R2 of approximately 0.76 and a Ratio of Performance to Deviation (RPD) of 2.12, showing a considerable improvement over the PLSR model. The superior performance of the ANN models can be attributed to their ability to capture complex, non-linear relationships between spectral data and pH values, which linear models like PLSR may miss.ConclusionThis research successfully demonstrated that hyperspectral imaging, in combination with machine learning algorithms, particularly ANN and PSO, can be an accurate and reliable method for the non-destructive prediction of pH in different plum cultivars. The hybrid approach used in this study, which combined DT for initial feature selection with PSO for optimal wavelength selection, enabled the models to predict pH values with very high accuracy, especially for the Khoni plum cultivar. This method can be used as an efficient tool in post-harvest quality control processes, helping to reduce waste and improve efficiency in the fruit supply chain. This work paves the way for the development of smart grading and sorting systems that can quickly and accurately assess fruit quality, benefiting both producers and consumers.
Image Processing
I. Ahmadi
Abstract
In the context of plant diseases, the selection of appropriate preventive measures, such as correct pesticide application, is only possible when plant diseases have been diagnosed quickly and accurately. In this study, a transfer learning model based on the pre-trained EfficientNet model was implemented ...
Read More
In the context of plant diseases, the selection of appropriate preventive measures, such as correct pesticide application, is only possible when plant diseases have been diagnosed quickly and accurately. In this study, a transfer learning model based on the pre-trained EfficientNet model was implemented to detect and classify some diseases in tomato crops, using an augmented training dataset of 2340 images of tomato plants. The study's findings indicate that during the model's validation phase, the rate of image categorization was roughly 5 fps (frames per second), which makes sense for a deep learning model operating on a laptop computer equipped with a standard CPU. Furthermore, the model was learned well because increasing the number of epochs no longer improved its accuracy. After all, the curves of the train and test accuracies, as well as the losses versus epoch numbers, remained largely horizontal for epoch numbers greater than 20. Notably, the highest coefficient of variation across these four cases was only 7%. Furthermore, the cells of the primary diagonal of the confusion matrix were filled with larger numbers in comparison with the values of the other cells; precisely, 88.8%, 7.7%, and 3.3% of the remaining cells of the matrix (cells of the primary diagonal excluded) were filled with 0, 1, and 2, respectively. The model's performance metrics are: sensitivity 85%, specificity 98%, precision 86%, F1-score 84%, and accuracy 85%.
Image Processing
O. Doosti Irani; M. H. Aghkhani; M. R. Golzarian
Abstract
Robotic harvesting in agriculture is an effective method for producing healthy fruit, reducing costs, and increasing productivity. Detecting and harvesting sweet peppers, however, remains a challenging task. This study aims to develop an unsupervised machine vision algorithm to recognize colored sweet ...
Read More
Robotic harvesting in agriculture is an effective method for producing healthy fruit, reducing costs, and increasing productivity. Detecting and harvesting sweet peppers, however, remains a challenging task. This study aims to develop an unsupervised machine vision algorithm to recognize colored sweet peppers using a combination of geometric features (Fast Point Feature Histogram- FPFH) and color features (H, S, and V). Depth images were captured using a Kinect v2 sensor, and a 3D model was reconstructed. After extracting the geometric and color features, data preprocessing involved undersampling to ensure balance and applying the Z-score criterion to eliminate outliers. Principal component analysis (PCA) was used to reduce the feature dimensions, and the K-means clustering model was implemented to categorize the data using six geometric features and three color features. The silhouette coefficient was employed to evaluate clustering quality, and human evaluation demonsterated that the algorithm achieved a detection accuracy of 95.10% for sweet peppers.
Image Processing
H. Koroshi Talab; D. Mohammad Zamani; M. Gholami Par-Shokohi
Abstract
Diagnosing plant diseases is an important part of crop management and can significantly affect the quantity and quality of production. Traditional methods of visual assessment by human observers are time-consuming, costly, and error-prone, making accurate diagnosis and differentiation between various ...
Read More
Diagnosing plant diseases is an important part of crop management and can significantly affect the quantity and quality of production. Traditional methods of visual assessment by human observers are time-consuming, costly, and error-prone, making accurate diagnosis and differentiation between various diseases difficult. Advances in agriculture have enabled the use of non-destructive machine vision systems for plant disease detection, and color imaging sensors have demonstrated great potential in this field. This study presents a framework for diagnosing early blight and late blight diseases in potatoes using a combination of Relief feature selection algorithms and Random Forest classification, along with color, texture, and shape features in three color spaces: RGB, HSV, and CIELAB (Lab*). The results indicated that the diagnostic accuracy for the early blight and late blight disease groups, as well as the healthy leaf group, were 94.71%, 95%, and 95.2%, respectively. The overall accuracy for disease classification was 95.99%. Additionally, the diagnostic accuracy for the early blight and late blight disease groups, along with the healthy leaf group, was 91.07%, 98.36%, and 98.93%, respectively, with an overall classification accuracy of 96.12%. After separating the diseased area from the healthy part of the leaf, a total of 150 features were extracted, including 45 color, 99 textural, and 6 shape features. The most effective features for disease detection were identified using a combination of all three feature sets. This study demonstrated that integrating these three sets of features can lead to a more accurate classification of potato leaves and provide valuable insights into the diagnosis and classification of potato diseases. This approach can help farmers and other plant disease specialists to accurately diagnose and manage potato diseases, and ultimately lead to an increase in product quality and yield.
Image Processing
H. Bagherpour; F. Fatehi; A. Shojaeian; R. Bagherpour
Abstract
In some countries, people commonly consume hazelnuts in their shells to extend shelf life or due to technological limitations. Therefore, open-shell hazelnuts are more marketable. At the semi-industrial scale, open-shell and closed-shell hazelnuts are currently separated from each other through visual ...
Read More
In some countries, people commonly consume hazelnuts in their shells to extend shelf life or due to technological limitations. Therefore, open-shell hazelnuts are more marketable. At the semi-industrial scale, open-shell and closed-shell hazelnuts are currently separated from each other through visual inspection. This study aims to develop a new algorithm to separate open-shell hazelnuts from cracked or closed-shell hazelnuts. In the first approach, dimension reduction techniques such as Sequential Forward Feature Selection (SFFS) and Principal Component Analysis (PCA) were used to select or extract a combination of color, texture, and grayscale features for the model’s input. In the second approach, individual features were used directly as inputs. In this study, three famous machine learning models, including Support Vector Machine (SVM), K-nearest neighbors (KNN), and Multi-Layer Perceptron (MLP) were employed. The results indicated that the SFFS method had a greater effect on improving the performance of the models than the PCA method. However, there was no significant difference between the performance of the models developed with combined features (98.00%) and that of the models using individual features (98.67%). The overall results of this study indicated that the MLP model, with one hidden layer, a dropout of 0.3, and 10 neurons using Histogram of Oriented Gradients (HOG) features as input, is a good choice for classifying hazelnuts into two classes of open-shell and closed-shell.
Image Processing
M. Nadafzadeh; A. Banakar; S. Abdanan Mehdizadeh; M. R. Zare-Bavani; S. Minaei
Abstract
IntroductionNowadays, machine vision systems are extensively used in agriculture. The application of this technology in the field can help preserve agricultural resources while reducing manual labor and production costs. In the field of agricultural automation, accurately detecting crop rows is recognized ...
Read More
IntroductionNowadays, machine vision systems are extensively used in agriculture. The application of this technology in the field can help preserve agricultural resources while reducing manual labor and production costs. In the field of agricultural automation, accurately detecting crop rows is recognized as a crucial and challenging issue for weed identification and the automatic guidance of machines. Therefore, it is necessary to explore practical solutions to optimize this process. Hence, the purpose of this study is the precise identification of basil cultivation rows to enable the automatic navigation of robots in the cultivation field.Materials and MethodsIn the first stage of this research, six images from each growth period of basil plants (third, fourth, and fifth week) were taken and weeds were removed from the area between the crop rows using three different methods of area opening, dimensional removal, and masking. In the next stage, six images of crop rows without weeds were examined by performing image processing operations and implementing several routing algorithms, namely, Hough transform, wavelet transform, Gabor filter, linear regression, and an additional algorithm proposed in this study. The output of each of these algorithms was compared with the ideal path identified by the user. For this purpose, after capturing an image, green areas were extracted from it by performing the segmentation process. By applying each of the routing algorithms to the image, plant cultivation lines were identified and their equations were determined. Finally, the performance of the designed robot was evaluated using the most appropriate routing algorithm.Results and DiscussionExamining the performance of three different methods of weed removal in three periods of plant growth (third, fourth, and fifth week) showed that during this interval, the masking method had the lowest error rate compared to the ideal path and the shortest average operation time of 1.64 seconds, followed by the dimensional removal and the area opening methods. Comparing the routes detected by different routing algorithms with the ideal routes and according to the results of the t-test at 5% probability level, the order of the studied routing methods from the most superior is as follows: the proposed algorithm, Gabor filter, linear regression, Hough transform and wavelet transform algorithm. Overall, the proposed algorithm had the highest rate of adaptation to the ideal path (with an average error of 3.65 pixels) and the shortest operation time (4.79 seconds) and was selected as the most appropriate routing algorithm and the performance of the designed robot was evaluated using it.ConclusionA reliable crop row detection algorithm can reduce production costs and preserve the environment. In this study, the masking method was used for removing weeds from the images. The new proposed routing algorithm has superior performance when compared with common routing algorithms such as the Gabor filter, linear regression, Hough transform, and wavelet transform. Additionally, it was shown that the designed robot using the proposed algorithm (with an average error of 3.65 pixels) has the desired performance.AcknowledgmentThe authors express appreciation for the financial support provided by Tarbiat Modares University.
Image Processing
S. Abdanan Mehdizadeh
Abstract
IntroductionAdopting new technologies for crop growth has the characteristics of improving disaster resistance and stress tolerance, ensuring stable yields, and improving product quality. Currently, the cultivation of seed trays relies on huge labor power, and further mechanization is needed to increase ...
Read More
IntroductionAdopting new technologies for crop growth has the characteristics of improving disaster resistance and stress tolerance, ensuring stable yields, and improving product quality. Currently, the cultivation of seed trays relies on huge labor power, and further mechanization is needed to increase production. However, there are some problems in this operation, such as the difficulty of improving the speed of a single machine, seedling deficiency detection, automatic planting, and controlling the quality, which need to be solved urgently. To solve these problems, there are already some meaningful attempts. Si et al. (2012) applied a photoelectric sensor to a vegetable transplanter, which can measure the distance between seedlings and the movement speed of seedlings in a seedling guide tube, to prevent omission transplantation. Yang et al. (2018) designed a seedling separation device with reciprocating movement of the seedling cup for rice transplanting. Tests show that the structure of the mechanical parts of the seedling separation device meets the requirements of seed movement. The optimization of the control system can improve the positioning accuracy according to requirements and achieve the purpose of automatic seedling division. Chen et al. (2020) designed and tested of soft-pot-tray automatic embedding system for a light-economical pot seedling nursery machine. The experimental results showed that the embedded-hard-tray automatic lowering mechanism was reliable and stable as the tray placement success rate was greater than 99%. The successful tray embedding rate was 100% and the seed exposure rate was less than 1% with a linear velocity of the conveyor belt of 0.92 m s-1. The experiment findings agreed well with the analytical results.Despite the sharp decline in Iran's water resources and growing population, the need to produce food and agricultural products is greater than ever. In the past, most seeds were planted directly into the soil, and many water resources, especially groundwater, were used for direct seed sowing and plant germination. One way to reduce the consumption of water, fertilizers, and pesticides is to plant seedlings instead of direct seed sowing. Therefore, the purpose of this study was dynamic modeling and fabrication of seed planting systems in seedling trays.Material and MethodsIn this experiment, Flores sugar beet seeds (Maribo company, Denmark) were used. The seedling trays had dimensions of 29.5*60 cm with openings and holes of 5.5 and 4 cm, respectively. To plant seeds in seedling trays, first, a planter arm was modeled and its position was obtained at any time. Then, based on dynamic modeling, the arm was constructed and a capacitive proximity sensor (CR30-15AC, China) and IR infrared proximity sensor (E18-D80NK, China) were used to find the location of seedling trays on the input conveyor and position of discharging arm, respectively. To achieve a stable and effective control system, a micro-controller-based circuit was developed to signal the planting system. The seed planting operation was performed in the seedling tray according to the coordinates which were provided through the image processing method. The planting system was evaluated at two levels of forward speed (5 and 10 cm s-1). Moreover, a smartphone program was implemented to monitor the operation of the planting system.Results and DiscussionThe planting system was assessed for sugar beet seeds using two levels of forward speed (5 and 10 cm s-1). The nominal capacity of this planter ranged from 3579 to 4613 cells per hour, with a miss and multiple implantation indices of 0.03% and 8.17%, respectively, in 3000 cells. Due to its planting accuracy, speed, and low energy consumption (25.56 watt-hours), this system has the potential to replace manual seeding in seedling trays.ConclusionIn the present study, a seed-sowing system for planting seedling trays was designed, constructed, and evaluated based on dynamic modeling. In the developed system, unlike previous research, planting location detection was conducted through image processing. Additionally, a smartphone program was established to monitor the operation of the planting system without interfering with its performance. This study demonstrates that image processing can successfully detect planting locations and can effectively improve efficiency over time for major producers.
Image Processing
Sh. Falahat Nejad Mahani; A. Karami
Abstract
IntroductionMaize is one of the most important cereal crops worldwide, providing staple food for people globally. Counting maize tassels provides essential information about yield prediction, growth status, and plant phenotyping, but traditional manual approaches are expensive and time-consuming. Recent ...
Read More
IntroductionMaize is one of the most important cereal crops worldwide, providing staple food for people globally. Counting maize tassels provides essential information about yield prediction, growth status, and plant phenotyping, but traditional manual approaches are expensive and time-consuming. Recent developments in technology, including high-resolution RGB imagery acquired by unmanned aerial vehicles (UAVs) and advanced machine-learning techniques such as deep learning (DL), have been used to analyze genotypes, phenotypes, and crops.In this study, we modified the YOLOv5s single-stage object detection technique based on a deep convolutional neural network and named it MYOLOv5s. We incorporated BottleneckCSP structures, Hardswish activation function, and two-dimensional spatial dropout layers to increase tassel detection accuracy and reduce overfitting. Our method's performance was compared with three state-of-the-art algorithms: Tasselnetv2+, RetinaNet, and Faster R-CNN. The results obtained from our proposed method demonstrate the effectiveness of MYOLOv5s in detecting and counting maize tassels. Materials and MethodsThe High-Intensity Phenotyping Site (HIPS) dataset was collected from the large field at the Agronomy Center for Research and Education (ACRE) of Purdue University, located in West Lafayette, Indiana, USA during the 2020 growing season. A Sony Alpha 7R-III RGB camera mounted on a UAV at a 20m altitude captured high-resolution orthophotos with a pixel resolution of 0.25 cm. The dataset consisted of two replications of 22 entries each for hybrids and inbreds, planted on May 12 using a two-row segment plot layout with a plant population of 30,000 per acre. The hybrids and inbreds in this dataset had varying flowering dates, ranging from 20 days between the first and last variety.This article uses orthophotos taken on July 20th and 24th to train and test the proposed deep network "MYOLOv5s." These orthophotos were divided into 15 images (3670×2150) and then cropped to obtain 150 images (608 × 2048) for each date. Three modifications were applied to the original YOLOv5s to form MYOLOv5s: BottleneckCSP structures were added to the neck part of the YOLOv5s, replacing some C3 modules; two-dimensional spatial dropout layers were used in the defect layer; and the Hardswish activation function was utilized in the convolution structures. These modifications improved tassel detection accuracy. MYOLOv5s was implemented in the Pytorch framework, and the Adam algorithm was applied to optimize it. Hyper-parameters such as the number of epochs, batch size, and learning rates were also optimized to increase tassel detection accuracy.Results and DiscussionIn this study, we first compared the original and modified YOLOv5s techniques, and our results show that MYOLOv5s improved tassel detection accuracy by approximately 2.80%. We then compared MYOLOv5s performance to the counting-based approach TasselNetv2+ and two detection-based techniques: Faster R-CNN and RetinaNet. Our results demonstrated the superiority of MYOLOv5s in terms of both accuracy and inference time. The proposed method achieved an AP value of 95.30% and an RMSE of 1.9% at 84 FPS, making it about 1.4 times faster than the other techniques. Additionally, MYOLOv5s correctly detected the highest number of maize tassels and showed at least a 17.64% improvement in AP value compared to Faster R-CNN and RetinaNet, respectively. Furthermore, our technique had the lowest false positive and false negative values. The regression plots show that MYOLOv5s provided slightly higher fidelity counts than other methods.Finally, we investigated the effect of score values on the performance of detection-based models and calculated the optimal values of hyperparameters.ConclusionThe MYOLOv5s technique outperformed other state-of-the-art models in detecting maize tassels, achieving the highest precision, recall, and average precision (AP) values.The MYOLOv5s method had the lowest root mean square error (RMSE) value in the error counting metric, demonstrating its accuracy in detecting and counting maize tassels.We evaluated the correlation between predicted and ground-truth values of maize tassels using the R2 score, and for the MYOLOv5s method, the R2 score was approximately 99.28%, indicating a strong correlation between predicted and actual values.The MYOLOv5s method performed exceptionally well in detecting tassels, even in highly overlapping areas. It accurately distinguished and detected tassels, regardless of their proximity or overlap with other objects.When compared to the counting-based approach TasselNetv2+, our proposed MYOLOv5s method showed faster inference times. This suggests that the MYOLOv5s method is computationally efficient while maintaining accurate tassel detection capabilities.
Image Processing
M. Fallah; E. Ghanbari Parmehr
Abstract
IntroductionRice is one of the most important main food sources in Iran and the world. The correct identification of the type of pest in the early stages of preventive action has a significant role in reducing the damage to the crop. Traditional methods are not only time-consuming but also provide inaccurate ...
Read More
IntroductionRice is one of the most important main food sources in Iran and the world. The correct identification of the type of pest in the early stages of preventive action has a significant role in reducing the damage to the crop. Traditional methods are not only time-consuming but also provide inaccurate results, As a result, precision agriculture and its associated technology systems have emerged. Precision agriculture utilizes information technology such as GPS, GIS, remote sensing, and machine learning to implement agricultural inter-farm technical measures to achieve better marginal benefits for the economy and environment. Machine learning is a division of artificial intelligence that can automatically progress based on experience gained. Deep learning is a subfield of machine learning that models the concepts of using deep neural networks with several high-level abstract layers. This capability has led to careful consideration in agricultural management. The diagnosis of disease and predicting the time of destruction, with a focus on artificial intelligence, has been the subject of much research in precision agriculture. This article presents, in the first step, a trained model of the Chilo suppressalis pest using data received from the smartphone, validated with the opinion of experts. In the second step, we introduce the developed system based on the smartphone. By using this system, farmers can share their pest images through the Internet and learn about the type of pest on their farm, and finally, take the necessary measures to combat it. This operation is done quickly and efficiently using the developed artificial intelligence. In the continuation of the article, the second part introduces the materials and methods, and the third part presents the results. The fourth section also discusses and concludes the research.Materials and MethodsChilo suppressalis is one of the most important pests of rice in temperate and subtropical regions of Asia. The conventional approach employed by villagers to gather the Chilo suppressalis pest entails setting up a light source above a pan filled with water infused with a pesticide. At sunset, these insects are attracted to the light and fall into the water in the pan. This method is known as optical trapping. After catching the pest using optical traps, they are collected from the water surface, and their photo is taken with a mobile phone based on the location of the optical trap.The proposed method in this research consists of three main steps. Firstly, the farmer utilizes the software provided by the extended version known as Smart Farm. The farmer captures an image of the Chilo suppressalis pest and sends it along with its location to the system. The Smart Farm software program carries out image processing and pest range detection operations. The user then verifies the accuracy of the pest detection. In the second step, the images sent by the farmer are processed by the pre-trained model within the system. The model analyzes the images and determines the presence of the pest. Finally, after identifying the type of pest, the results, along with recommended methods for pest control, are sent back to the farmer.In summary, In this method, farmers employ the Smart Farm software to capture and transmit images of the Chilo suppressalis pest. The captured images then undergo image processing and pest range detection as the next steps in the process. The results, including pest identification and control methods, are then returned to the farmer.Results and DiscussionThe model has been designed with 400 artificial neural network processing units (APCs), achieving accuracy percentages of 88% and 92%. To conduct a more detailed study of the proposed model, the statistical criteria of recall and F-score were used. Based on the calculations, the trained model demonstrated a recall score of 91%. This criterion shows that the model was able to identify a large percentage of what was expected to be identified by the model. Additionally, the F-score, with an acceptable percentage of 88%, confirmed the accuracy of the trained model.ConclusionResearchers have always been highly interested in the valuable data freely provided by farmers for their studies and analyses. In this study, an intelligent system was designed for identifying types of pests such as worms and stalk eaters, which can automatically determine the pest type from the image sent by the farmer using artificial intelligence and deep learning. By utilizing the developed system, farmers can be informed of the type of pest present on their farm in the shortest possible time, with minimal required software training.
Image Processing
D. Mohammad Zamani; S. M. Javidan; M. Zand; M. Rasouli
Abstract
The main purpose of this study was to provide a method for accurately identifying the position of cucumber fruit in digital images of the greenhouse cucumber plant. After balancing the brightness histogram of the desired image, it multiplies the image with a window containing the image of a cucumber ...
Read More
The main purpose of this study was to provide a method for accurately identifying the position of cucumber fruit in digital images of the greenhouse cucumber plant. After balancing the brightness histogram of the desired image, it multiplies the image with a window containing the image of a cucumber fruit, which causes larger coefficients to be obtained in areas with suspected cucumber. By extracting these local maximums, clusters of initial points are obtained as possible windows of cucumber existence. Then, in order to accurately detect the location of the cucumbers, these points and areas around them are referred to a neural network that has been trained using a number of images including cucumber images, non-cucumber images and their optimal responses. The proposed method was implemented in the Simulink toolbox of MATLAB software. The proposed method was then simulated using this network structure and tested on 120 images obtained from a greenhouse by a digital camera. The areas obtained from this network led to the accurate detection of the location of the cucumbers in the image. The proposed method was then simulated and tested on 120 images. The proposed method had a low error and was able to detect high levels of cucumber fruit in the images. This detection took an average of 5.12 seconds for each image. The accuracy of the network in correctly identifying the position of the cucumber fruit in the images was 95.3%. This method had low error and was able to detect a high rate at a good time of cucumber fruits in discover images.
Image Processing
A. Mesri; F. Rahimi-Ajdadi; I. Bagheri
Abstract
IntroductionRice is the fourth most consumed grain worldwide. In recent years, monitoring the area under rice cultivation; as a strategic crop in Gilan province has become more important because of the uncontrolled migration of residents of the southern provinces to it. Remote sensing is one of the practical ...
Read More
IntroductionRice is the fourth most consumed grain worldwide. In recent years, monitoring the area under rice cultivation; as a strategic crop in Gilan province has become more important because of the uncontrolled migration of residents of the southern provinces to it. Remote sensing is one of the practical tools to study the trend of changes in the area under cultivation of agricultural and horticultural products on a large scale and in a short time. This technique can help policymakers to make true and timely decisions. The aim of this study is to estimate the area under rice cultivation in Kiashahr county of Gilan province.Materials and MethodsThe images of the TM sensor of Landsat 5 satellite and the OLI sensor of Landsat 8 satellite were used to prepare land use maps. First, geometric and atmospheric corrections were made to the images. Then, supervised classification using the maximum likelihood algorithm was used to prepare land use maps for each year. Seven main classes/land covers, based on the available data of the area were determined: rice-land, semi-dense forest, sparse forest, built-up area (towns and other urbanized areas), waterbody, sandy area and other areas. Then, the area of each land use was calculated by GIS, and their changes were compared.Results and DiscussionOverall accuracy and kappa coefficient of classification were 98.45% and 0.98 for 2000, 97.59% and 0.97 for 2010, and 98.72% and 0.98 for 2020, respectively. According to the results, rice land area decreased by 4.42% from 2000 to 2010. It also had a decrease of 2.64% between 2010 and 2020. In total, rice lands decreased by 6.94% between 2000 and 2020, so its area has decreased to 10311.69 hectares. This downward trend can be due to the conversion of rice land to the built-up area. The area of semi-dense forest decreased by 47.48% between 2000 and 2010, but its downward trend decreased to 26.36% between 2010 and 2020. In total, semi-dense forest area decreases by 61.32%, equal to 682.25 hectares over a period of 20 years. This is due to the uncontrolled cutting of trees and the change of land use from semi-dense forests to sparse forests and built-up areas. Also, during this period, built-up areas and sparse forests have grown by 67.94% and 18.73%, respectively. But, semi-dense forests, water bodies and sandy areas have decreased by 61.32%, 4.91% and 61.48%, respectively.ConclusionThe reduction rate in the area of rice land and semi-dense forest classes between 2010 and 2020 was lower than the ten-year period before, which can be attributed to the adoption of restrictive laws and more inspections by relevant organizations. However, the downward trends in these land uses have continued over the past decade. Meanwhile, the increase of 67.94% of built-up lands indicates that the lost lands in the forest and rice land classes have been converted into the built-up area. The rate of land-use change in the built-up class has the highest rate among the studied classes. This result indicates the need for serious attention to land-use change in the rural area more than before. Another point is that there was a growth in sparse forests between 2000 and 2010, and then a reverse trend was observed between 2010 and 2020, which shows that in a period of 10 years, deforestation has taken place, and in 10 years later, the lands from these destructions have been converted to the built-up area. As a result, serious attention to natural resource organizations is necessary. It is considered that there was a deliberate destruction of forests over time with the aim of personal profit.
Image Processing
Z. Azizpour; H. Vahedi; A. N. Lorestani
Abstract
IntroductionPistachio or Green Gold is one of the most important agricultural crops and is especially important for Iranian exports. A group of pistachio's pests mainly feed on pistachio, among which Idiocerus stali is very important. Conventional methods for identifying insects using identification ...
Read More
IntroductionPistachio or Green Gold is one of the most important agricultural crops and is especially important for Iranian exports. A group of pistachio's pests mainly feed on pistachio, among which Idiocerus stali is very important. Conventional methods for identifying insects using identification keys are time-consuming and costly. Due to the rapid development of the Pistachio industry, the use of artificial intelligence techniques such as image processing, for identification and population monitoring is highly recommended. On the other hand, little research was carried out on I. stali. Therefore, in this research, I. stali was selected as a target insect for the identification and counting on sticky yellow cards using image processing techniques and artificial neural networks. The purpose of this study was to determine the feasibility of I. stali identification algorithm by image processing, to determine the possibility of separation and counting of I. stali from other non-target insects by artificial neural network and to determine its accuracy in identification of I. Stali.Materials and MethodsIdiocerus stali was selected as the target insect for identification. Sticky yellow cards were used for collecting samples. Taking the photos with the help of a SONY Handycam Camera, which had a 12-megapixel resolution and G lens, was carried out (SONY, HDR-XR500, CMOS, SONY Lens G, Made in Japan). Then insects were counted on each card manually and the data was recorded. The data, which were digital images of yellow sticky cards, were imported into the MatLab R2017b software environment. A total of 357 color properties and 20 shape's features for the identification of I. stali were extracted by an image processing algorithm. Color properties were divided into two categories of mean and standard deviation and characteristics related to vegetation indices. An ANN-PSO (Artificial Neural Network hybrid method-Particle Swarm Optimization) algorithm was used to select the effective features. The selected effective characteristics for insect classification were: Color index for extra collective vegetation related to HSL color space, normalized difference index for LCH color space, gray channel for color space YCbCr, second component index minus third component for color space YCbCr, area and mean of the first, second and third components of color space Luv.Results and DiscussionComparing the results with the results of Qiao et al. (2008), we found that in his study, which divided the data into three categories, for medium and high-density groups, the detection rate was 95.2% and 94.6%, respectively. On the other hand, in low densities (less than 10 trapped insects); its detection rate was 72.9%, while the detection rate of the classifier system designed in this study for different densities of trapped insects, was identical and equal to 99.59%. Also, comparing the results of this study with Espinoza et al. (2016), we found that their algorithm in whiteflies detection had a high accuracy of about 0.96 on a sticky yellow card, while the Thrips identification algorithm accuracy was 0.92 on a sticky blue card. As stated above, the correct detection rate of I. stali by the algorithm designed in this study was 99.72%.ConclusionThe results showed the feasibility of the new method for identifying the pest insects without destroying them on the farm and in natural light conditions and in a short time and with very high accuracy. This suggests that this algorithm can be applied to the machine vision system and can be used in future in the construction of agricultural robots.
Image Processing
A. Yousefvand; J. Amiri Parian
Abstract
IntroductionControl of walnut diseases and pests requires the mapping of the extent of contamination within possible shortest time. Therefore, it is necessary to develop systems to detect and determine the prevalence and location of contamination for researchers and gardeners. Image processing has been ...
Read More
IntroductionControl of walnut diseases and pests requires the mapping of the extent of contamination within possible shortest time. Therefore, it is necessary to develop systems to detect and determine the prevalence and location of contamination for researchers and gardeners. Image processing has been proposed as an approach to determine the extent and type of damage to different products in farms and gardens. The aim of this study was to design an algorithm based on the processing of walnut leaf images under natural light conditions in order to provide a rapid and non-destructive detection of diseases for the protection of trees using imaging methods. In this research, the possibility of detecting Anthracnose disease was investigated by processing walnut leaf images. The disease was detected using in situ images taken from the leaves to provide the basis for designing application software on smart mechatronic systems. Materials and MethodsImages of leaves on walnut trees were taken under outdoor light conditions. Color and morphological properties extracted from the images were used to detect the pest on the leaves. Gnomonia leptostyla disease diagnostic algorithm was based on process of color and morphological characteristics, leaves background and disease-stained spots. The range of changes in R, G, and B indices was obtained in histograms and then two-dimensional spaces were analyzed statistically on GR, GB, and BR planes. All points from these regions were used as statistical samples, for which bivariate regressions of GR, GB, and BR were obtained as y = b0 + b1x. Segments containing anthracnose spots from the leaves were segregated by extracting the coordinates of the points in each side on the RGB color space cube. Finally, anthracnose content was detected based on the number of spots detected by the algorithms. The percentage of contamination was used to determine the amount of contamination in each imaged area.Results and DiscussionExamination of the colored spaces indicated that the domain of the anthracnose color components on the GR side has nothing in common with the color components of the leaves. The analysis of color space data revealed that the leaves and anthracnose were more distinguishable on the GB and RB sides, respectively. According to the histogram of the HSV color space, anthracnose spots were isolated from the leaves by determining the H range. In the evaluation of the proposed method for diagnosis of anthracnose, the infection severity calculated by the algorithm with the true infection intensity. T-test results for comparing the mean of the two infection intensity samples showed no significant differences between the two groups at 1% probability level. ConclusionThe evaluation of the proposed method showed a 98% segregation accuracy for G. leptostyla detection method. Based on the results, the proposed method for detecting anthracnose spots is suitable for determining the contamination severity in the imaged areas.
Image Processing
A. Jahanbakhshi; K. Kheiralipour
Abstract
Introduction Carrot is one of the most important agricultural products used by millions of people all over the world. Quality assessment of agricultural products is one of the most important factors in improving the marketability of agricultural products. In the market, carrots with irregular shapes ...
Read More
Introduction Carrot is one of the most important agricultural products used by millions of people all over the world. Quality assessment of agricultural products is one of the most important factors in improving the marketability of agricultural products. In the market, carrots with irregular shapes are not commonly picked by customers due to their appearance. This causes to remain those carrots in the market for a long time and then decay. Therefore, adopting an appropriate method for sorting and packaging this product can increase its desirability in the market. Packaging and sorting of carrots by workers bring about many problems such as high cost, product waste, etc. Image processing systems are modern methods which have different applications in agriculture including sorting of different products. The aim of this study was to implement a machine vision system to classify carrot based on their shape using image processing. Materials and Methods In this study, 135 carrot samples with different shapes (56 regulars and 79 irregulars) were selected and their images were obtained through an imaging system. First, an expert divided the carrots into, two categories according to their shapes. The carrots which had irregular shape were those with double or triple roots, cracked carrots, curved carrots, damaged carrots, and broken ones and those with upright shapes were considered as regular shape carrot. After imaging, image processing was started by an algorithm programmed in Matlab R2012a medium. Then some shape features such as length, width, breadth, perimeter, elongation, compactness, roundness, area, eccentricity, centroid, centroid non-homogeneity, and width non-homogeneity were extracted. After the selection of efficient features, artificial neural networks and support vector machine were used to classify the efficient features. Results and Discussion The number of neurons in the hidden layers of artificial neural network models were varied to find the optimal model. The highest percentage of the correct classification rate (98.50%) belonged to the structure of 2-10-16, which in fact has 16 neurons in the input layer, 10 neurons in the hidden layer and 2 neurons in the output layer. This model has also the lowest mean squared error and the highest correlation coefficient of the test data, 0.90 and 2.52, respectively. This network was a feed forward back propagation error type and the activation functions in hidden and output layers were Tansig and Perlin, respectively. The correct classification rate of the support vector machine method was 89.62%. The confusion matrix of support vector machine method showed that out of 56 usual samples, 42 specimens were correctly identified but 14 samples were mistakenly classified as unusual carrots. All 79 carrots with unusual shapes were correctly classified. The results obtained from the comparison of the performance of the two methods, the neural network method has a good superiority than the support vector machine for classification. Conclusion In this research, the classification of carrots was based on its appearance. At first the physical characteristics and appearance attributes of the carrot samples were extracted and processed using image processing. Image analysis was included the classification of samples into two usual and unusual shapes, which to classify the extracted properties two methods were used: the artificial neural network (ANN) and support vector machine (SVM). The classification accuracy of the ANN method was higher than SVM. It can be said that the image processing method can be used to improve the traditional method for grading the carrot product in new ways. So, the marketability of the product will be increased, and thus its losses will be reduced. Also, the image processing technique can be used as a simple, fast and non-destructive alternative to other methods of extracting geometric properties of agricultural products. Finally, it can be stated that image processing method and machine vision are effective ways for improving the traditional sorting techniques for carrots.
Image Processing
A. Heidari; J. Amiri Parian
Abstract
Introduction Lack of water resources, increasing demands for food, the optimal use of water and land, and food security are of the most important reasons for the development of greenhouses in the country. The benefits of greenhouse cultivation consisted of the possibility to produce off-season, increase ...
Read More
Introduction Lack of water resources, increasing demands for food, the optimal use of water and land, and food security are of the most important reasons for the development of greenhouses in the country. The benefits of greenhouse cultivation consisted of the possibility to produce off-season, increase harvest period, reduce the production costs, increase economic efficiency and etc. Regarding the conditions of the greenhouse, in terms of temperature and humidity, a site is susceptible to contamination with various pests and diseases, which can cause a lot of damages to the products. So, for a high-quality product, identification and timely control of pests are necessary. The need for spraying in a timely manner, with a sufficient number of times, is to have accurate information on the population of pests in a greenhouse environment at different times. Whiteflies, thrips, and aphids are among the most commonly known harmful insects in the world, causing severe damages to greenhouse plants. Materials and Methods Twenty yellow sticky cards were randomly selected in different parts of the greenhouse of cucumbers in the Amzajerd district of Hamadan. From each card, 45 photos were taken with Canon IXUS 230HS digital camera with a resolution of 12.1 Megapixels at a distance of 20 centimeters. Before each image processing, trapped insects were initially identified and counted by three entomologists. At this stage, three types of insects (two harmful insects, whitefly and thrips and non-harmful insect) were identified. Then the images were transferred to Matlab software. The algorithm of identifying and counting the whitefly was the following six steps: Step 1: Convert the original image to the gray level image Step 2: Correcting the effects of non-uniform lighting Step 3: Determine the optimal threshold and convert the gray level image to the binary image Step 4: Remove objects smaller than Whitefly Step 5: Fill the holes in the image Step 6: Counting broken segments The algorithm of identifying and counting the thrips was the following eight steps: Step 1: Convert the original image to the gray level image Step 2: Correcting the effects of non-uniform lighting Step 3: Determine the optimal threshold and convert the gray level image to the binary image Step 4: Prepare image negatives Step 5: Remove objects smaller than the thrips Step 6: Remove the thrips and isolate the rest of the objects Step 7: Split the thrips Step 8: Count the thrips Results and Discussion Relative accuracy, root mean square error (RMSE) and Coefficient of variation of the RMSE of Whitefly counting in image processing system were 94.4%, 15.3 and 5.5% respectively. The results of the T-test between two methods indicated that there was no significant difference between them. The mean relative accuracy, root mean square error (RMSE) and Coefficient of variation of the RMSE of the thrips count in the image processing system were 87.4%, 18 and 5.9% respectively. There was no significant difference between the two methods. Conclusion The proposed image processing algorithm was able to detect whiteflies and thrips with a relative accuracy of 94.5% and 87.4%, respectively. In addition to simplicity, this method has the ability to adapt to different conditions. Also, with some changes in the proposed algorithm, the system will also be able to identify other pests. In order to design an intelligent spray system in the greenhouse, the population of pests needs to be monitored frequently, so the identification and counting of pests will be necessary for the intelligent spray system.
Image Processing
P. Ataieyan; P. Ahmadi Moghaddam; E. Sepehr
Abstract
Introduction The color of soil depends on its composition and this feature is easily available and rather stable. Fast and accurate determination of soil organic matter distribution in the agricultural fields is required, especially in precision farming. General laboratory methods for determining the ...
Read More
Introduction The color of soil depends on its composition and this feature is easily available and rather stable. Fast and accurate determination of soil organic matter distribution in the agricultural fields is required, especially in precision farming. General laboratory methods for determining the soil organic carbon are expensive, time-consuming with many repetitions, and high consumption of chemicals. Soil scientists use the Munsell soil color diagrams to define the soil color. Due to the nature of Munsell color diagrams; this system is less suitable for recognizing exact color of the soil because of weak relationship and limited number of chips. Fast methods like image processing, colorimetric and spectroscopy provide a description of most physical characteristics of the soil color. Some of the advantages of using digital cameras was used in this study, are simple sampling of screened soil, being free from chemicals and toxic materials and being fast, inexpensive and precise. Materials and Methods In this research, 80 A-horizon (0-10 cm) soil samples were collected from various agricultural soils in west Azerbaijan, in the North West of Iran. Soil texture of these fields was loam clay and clay. The amount of organic carbon in samples was determined. The camera was installed at the distance of 0.5 m from the Petri dish on the lighting compartment. Captured images with the digital camera were saved in RGB color space. Processing operations were done by MATLAB 2012 software. The features extracted from the color images are used to model the soil organic carbon including the color features in different spaces. Four-color spaces including RGB, HSI, LAB and LUV were studied to find the relation between the color and the soil organic carbon. Results and Discussion The correlation of R component in the RGB model shows a strong single-parameter relation with the organic carbon as R2=0.83. This good relationship can be due to the compound information of the red color component on both brightness and chromaticity dimension. The results also show that the organic carbon has a relatively strong correlation with the light parameters, intensity and lightness in the HSI, Lab and LUV color spaces respectively. It also has a weak correlation with other parameters, since they cannot have a proper linear correlation with organic carbon due to their structural nature. Results show that the highest correlation is obtained when the R and G components participate in modeling and the component B is omitted. One explanation of this high correlation could be the high sensitivity of component B to the intensity and the angle of light. Even a small change in light changes this component. Thus, in order to reduce the effect of this component, it is better to omit it from the models and make models independent of it. In next section, 51 data were used to train neural network, 14 data were used to test the network and 12 data for network validating. The amount of soil organic carbon was output of the neural networks that was estimated after training using the color component values of each segment. To assess the accuracy of the network, estimated values and actual values of each sample were plotted in a graph. The minimum MSE values were 7.28e-6 with 16 neurons, 3.77e-6 with 14 neurons, 4.8e-3 with 10 neurons and 3.77e-6 with 12 neurons for RGB, HSI, Lab and LUV color spaces respectively. Conclusion The availability of digital cameras, possibility to use it in different situations, being inexpensive and providing many samples are the advantages of this method to estimate the soil organic carbon amount. Therefore, digital photography can be used as an analytical method to evaluate the soil fertility. It also requires a low cost of sample testing, and can provide a good possibility of time and place classification for studying a vast area. However to develop more reliable models, more effort is needed, such as collecting more soil samples of different areas that include a wide range of soil features.
Image Processing
F. Behzadi Pour; M. Ghasemi-Nejad Raeini; M. A. Asoodar; A. Marzban; S. Abdanan Mehdizadeh
Abstract
Introduction Today, attention to safety and environmental issues in all sectors in agriculture, industry and services is very important. Chemical poisons play an important role in rapid progress of agricultural products. Every year about 25 to 35 percent of the world's crops are affected by insects, ...
Read More
Introduction Today, attention to safety and environmental issues in all sectors in agriculture, industry and services is very important. Chemical poisons play an important role in rapid progress of agricultural products. Every year about 25 to 35 percent of the world's crops are affected by insects, weeds and plant pathogens disappear and this figure would be raised to 80% if no control was applied. Drift problem and its devastating effects are the most important issue which related to users and sprayers manufacturers. Spray drift reduction and improvements in the efficiency of pesticide application processes are global goals. Where ever spraying is applied, drift will be produced and it must be controlled by controlled of the droplet size. The application of these sprayers is the high in the farms (the number of 2303 in Iran). So, this research was carried out to improve the quality of work in these sprayers by studying the droplets diameter and the spray quality index. Materials and Methods The research was conducted at the University of Khouzestan Ramin Agriculture and Natural Resources. Tests were done with 20 m of water sensitive papers at a distance of 2 meters from each other. To evaluate the technical items affecting on drift, an experiment was conducted using a turbo liner sprayer (TURBINA S.A. 800) and the John Deer (JD) 3140 tractor. A completely randomized factorial design was applied. By using 3 replications and the factors were spraying pressure applying three levels (10, 25 and 35 bar), the fan speed with two levels (1998 and 2430 rpm) and forward speed with two levels (9 and 13.5 km hr-1). The sprayer started the application, spraying a solution of water and tracer (yellow Tartrazine E 102), 15m before the water sensitive papers and then moved over the water sensitive papers. The spraying was continued 15 m after the end of the sampling area. After spraying, sensitive papers were photographed and then volume diameter of 50% (DV50) and median numerical diameter (NMD) and spraying quality indicator were calculated. A Spectrophotometry device at the wavelength of 427 nm, Image J and sas 9.2 software were used for measurement. This research was carried out in accordance with the calendar crop canola spraying in field conditions and the weather was calm that the wind speed was 0- 2.5 km hr-1, relative humidity was 29.7% - 32.5% and air temperature was 18.8˚C – 20.7˚C. Results and Discussion According to the results sprayer pressure, fan speed and forward speed were shown significantly different (P≤0.01) on the volume diameter of 50% (DV50) and median numerical diameter (NMD). The effect of spraying pressure on distributing quality indicator was shown significant (P ≤ 0.01), but the fan and forward speed did not shown any significant effect. Mean comparison of the interaction of pressure and forward speed on the spray quality index and the number median diameter were shown significant (P ≤ 0.01), but they did not shown any significant effect on the volume diameter of 50% (DV50). With increasing spraying pressure and fan speed, the droplet size, volume diameter of 50% (DV50) at 72% and numerical median diameter (NMD) at 69% and distributing quality indicator at 46% were decreased that were corresponded with the result of Czaczyk et al. (2012), Peyman et al. (2011), Nuyttens et al. (2009) and Landers and Farooq (2004). With increasing spraying pressure and forward speed, the droplet size, numerical median diameter (NMD) at 63% and distributing quality indicator at 35% were decreased that these resulted were corresponded with the results of Naseri et al. (2007) and Dorr et al. (2013). Conclusion With increasing spraying pressure, fan and forward speed, the droplet size, volume diameter of 50% (DV50) and numerical median diameter (NMD) were decreased. Therefore, spraying quality indicator was decreased. The maximum pressure (35 bars), maximum fan speed (2430 rpm) and maximum forward speed (13.5 km hr-1) were able to produce the minimum spraying quality indicator (10.3). At the minimum pressure (10 bars), maximum fan speed (2430 rpm) and minimum forward speed (9 km hr-1), the maximum spraying quality indicator (2.91) was resulted.
Image Processing
H. Asaei; A. A. Jafari; M. Loghavi
Abstract
IntroductionIn conventional methods of spraying in orchards, the amount of pesticide sprayed, is not targeted. The pesticide consumption data indicates that the application rate of pesticide in greenhouses and orchards is more than required. Less than 30% of pesticide sprayed actually reaches nursery ...
Read More
IntroductionIn conventional methods of spraying in orchards, the amount of pesticide sprayed, is not targeted. The pesticide consumption data indicates that the application rate of pesticide in greenhouses and orchards is more than required. Less than 30% of pesticide sprayed actually reaches nursery canopies while the rest are lost and wasted. Nowadays, variable rate spray applicators using intelligent control systems can greatly reduce pesticide use and off-target contamination of environment in nurseries and orchards. In this research a prototype orchard sprayer based on machine vision technology was developed and evaluated. This sprayer performs real-time spraying based on the tree canopy structure and its greenness extent which improves the efficiency of spraying operation in orchards. Materials and MethodsThe equipment used in this study comprised of three main parts generally: 1- Mechanical Equipment 2- Data collection and image processing system 3- Electronic control systemTwo booms were designed to support the spray nozzles and to provide flexibility in directing the spray nozzles to the target. The boom comprised two parts, the vertical part and inclined part. The vertical part of the boom was used to spray one side of the trees during forward movement of the tractor and inclined part of the boom was designed to spray the upper half of the tree canopy. Three nozzles were considered on each boom. On the vertical part of the boom, two nozzles were placed, whereas one other nozzle was mounted on the inclined part of the boom. To achieve different tree heights, the vertical part of the boom was able to slide up and down. Labview (version 2011) was used for real time image processing. Images were captured through RGB cameras mounted on a horizontal bar attached on top of the tractor to take images separately for each side of the sprayer. Images were captured from the top of the canopies looking downward. The triggering signal for actuating the solenoid valves was initially sent to the electronic control unit as the result of image processing. Electronic control unit was used to adjust the right time of spraying based on the signals received from the encoder to precisely spray the targeted tree. The distance between the camera and spraying nozzles was considered in the microcontroller program. The solenoid would be turned off and stop the spraying when the vision system realized that there was a gap between the trees.Water sensitive papers (WSP) were used to evaluate the sprayer performance in prompt spraying of the trees and cutting off at hollow spaces between the trees. Water sensitive papers were attached to three ropes extended along the movement direction of the tractor at top, middle, and bottom of the trees so that each tree comprised 9 WSPs whereas other 9 WSPs were placed at each gap between two successive trees. Three levels of forward speed of 2 km h-1, 3.5 km h-1and 5 km h-1 was tried in these experiments to evaluate the effect of forward speed on spraying performance. Experiments were conducted in three replications. Liquid consumption of the sprayer designed in this research was compared with the conventional overall spraying.Results and DiscussionAnalysis of variances of data gained from water sensitive paper corresponding to the sprayed areas showed a significant effect of forward speed on prompt spraying.Comparison of means of spraying coverage on WSPs at different forward speeds with four replications showed that the maximum amount of targeted sprayed pesticide has been achieved at the lowest speed (2 km h-1) while the lowest amount of sprayed was seen at the maximum speed. Although higher forward speed is preferred because it increases the operation capacity of the sprayer, increasing the forward speed of the sprayer reduces the coverage density of the liquids on WSPs because the output rates of the nozzles are constant. Therefore, in cases that higher forward speed is demanded, more nozzles should be added to the sprayer booms Comparison between the liquid consumptions of the proposed system and conventional overall spraying showed that in this study, up to 54% less material has been used for the experiment in olive orchard. ConclusionsThe sprayer designed in this study was able to detect the gap between the trees in orchards using a machine vision system to stop the spraying on places where no tree exists. Results showed that employing the new sprayer decreased a significant amount of spray liquids which can be important both economically and environmentally. Considering to lack of pesticide spraying in the hollow spaces between the trees, certainly, more significant reduction is expected to achieve in young orchards where trees are small and there are larger gaps between the trees
Image Processing
A. R. Abdollahnejad Barough; M. Adelinia; M. Mohamadi
Abstract
Introduction: Pistachio nut is one of the most important agricultural products of Iran and it is priced due to the quality and type. One of the significant factors of pistachio cost is its type in terms of shell. Filled split pistachio nut has the most quality and is utilized as nuts, while the closed ...
Read More
Introduction: Pistachio nut is one of the most important agricultural products of Iran and it is priced due to the quality and type. One of the significant factors of pistachio cost is its type in terms of shell. Filled split pistachio nut has the most quality and is utilized as nuts, while the closed shell type has lower cost, at the same time is economically efficient in food industry such as confectionery. Now, pistachio sorting is performed usually by human and sometimes using electromechanical apparatuses. Classification of pistachio by human is time consuming and is done with an unacceptable accuracy, on the other hand, electromechanical and electro optical apparatuses damages pistachio because the mechanism used in them while separating. So, the need to develop automated systems that could be implemented by intelligent ways is evident to increase the speed and accuracy of classification.Materials and Methods: In this study, 300 samples of pistachios contains 100 Filled split, 100 Filled non-split and 100 split blank nuts ones are used. The training set consisted of 60 samples of each type of opened nuts, closed and empty opened shell nuts a total of 180 samples and the evaluation set consisted of 40 samples of each type of opened shell, closed shell and empty opened shell nuts a total of 120 samples. The principle of this study is implemented in two steps: 1) sample imaging and image processing to extract features 2) fuzzy network design based on the characteristics of data and training.To select useful features from the hypothesis, C4.5 decision tree is used. C4.5 algorithm makes a greedy top to bottom search on the hypothesis, and is made by the question what feature must be at the root of the tree. By the help of statistical methods, extracted features from the images were prioritized and the most appropriate features for classification of training set were selected. The algorithm chooses the best features as their number is minimum. Finally, a total amount of the second moment (m2) and matrix vectors of image were selected as features. Features and rules produced from decision tree fed into an Adaptable Neuro-fuzzy Inference System (ANFIS). ANFIS provides a neural network based on Fuzzy Inference System (FIS) can produce appropriate output corresponding input patterns.Results and Discussion: The proposed model was trained and tested inside ANFIS Editor of the MATLAB software. 300 images, including closed shell, pithy and empty pistachio were selected for training and testing. This network uses 200 data related to these two features and were trained over 200 courses, the accuracy of the result was 95.8%. 100 image have been used to test network over 40 courses with accuracy 97%. The time for the training and testing steps are 0.73 and 0.31 seconds, respectively, and the time to choose the features and rules was 2.1 seconds.Conclusions: In this study, a model was introduced to sort non- split nuts, blank nuts and filled nuts pistachios. Evaluation of training and testing, shows that the model has the ability to classify different types of nuts with high precision. In the previously proposed methods, merely non-split and split pistachio nuts were sorted and being filled or blank nuts is unrecognizable. Nevertheless, accuracy of the mentioned method is 95.56 percent. As well as, other method sorted non-split and split pistachio nuts with an accuracy of 98% and 85% respectively for training and testing steps. The model proposed in this study is better than the other methods and it is encouraging for the improvement and development of the model.
Image Processing
S. H. Payman; A. Bakhshipour Ziaratgahi; A. A. Jafari
Abstract
Introduction: Rice is a very important staple food crop provides more than half of the world caloric supply. Rice diseases lead to significant annual crop losses, have negative impacts on quality of the final product and destroy plant variety. Rice Blast is one of the most widespread and most destructive ...
Read More
Introduction: Rice is a very important staple food crop provides more than half of the world caloric supply. Rice diseases lead to significant annual crop losses, have negative impacts on quality of the final product and destroy plant variety. Rice Blast is one of the most widespread and most destructive fungal diseases in tropical and subtropical humid areas, which causes significant decrease in the amount of paddy yield and quality of milled rice.Brown spot disease is another important fungal disease in rice which infects the plant during the rice growing season from the nursery period up to farm growth stage and productivity phase. The later the disease is diagnosed the higher the amount of chemicals is needed for treatment. Due to high costs and harmful environmental impacts of chemical toxins, the accurate early detection and treatment of plant disease is seemed to be necessary.In general, observation with the naked eye is used for disease detection. However, the results are indeed depend on the intelligence of the person performing the operation. So usually the accurate determination of the severity and progression of the disease can’t be achieved. On the other side, the use of experts for continuous monitoring of large farms might be prohibitively expensive and time consuming. Thus, investigating the new approaches for rapid, automated, inexpensive and accurate plant disease diagnosis is very important.Machine vision and image processing is a new technique which can capture images from a scene of interest, analyze the images and accurately extract the desired information. Studies show that image processing techniques have been successfully used for plant disease detection.The aim of this study was to investigate the ability of image processing techniques for diagnosing the rice blast and rice brown spot.Materials and Methods: The samples of rice leaf infected by brown spot and rice blast diseases were collected from rice fields and the required images were obtained from each sample.The images of infected leaves were then introduced to image processing toolbox of MATLAB software. The RGB images were converted to gray-scale. Using a suitable threshold, the leaf surface was segmented from image background and the first binary image was achieved. Leaf image with zero background pixels was obtained after multiplying the black-and-white image to original color image. The resulting image was transformed to HSV color space and the Hue color component was extracted. The final binary image was created by applying an appropriate threshold on the image that obtained from Hue color component.As there was a high color similarity between the symptoms of two diseases, it was not possible to use Hue color component to distinguish between them. Therefore the shape processing was applied.Four dimensionless morphological features such as Roundness, Aspect Ratio, Compactness and Area Ratio were extracted from stain areas and based on these features, disease type diagnosis was performed.Results and Discussion: Results showed that the proposed algorithm successfully diagnosed the diseases stains on the rice leaves. A detection accuracy of 97.4±1.4 % was achieved.Regarding the results of t-test, among the extracted shape characteristics, only in the case of Area Ratio, there was no significant difference between two disease symptoms. While in the case of Roundness, Aspect Ratio and Compactness, a highly significant difference (P<0.01) was discovered and revealed between rice blast and rice brown spot stains. The developed algorithm was capable of distinguishing between disease symptoms with an exactness of over 96.6%. This means that of the 60 samples (30 samples rice blast and 30 samples of rice brown spot); only two were placed in the wrong category.Conclusions: It was concluded from this study that image processing technique can not only accurately determine whether the rice is healthy or infected but also can determine the type of plant disease with reliable precision. Considering the fact that plant diseases spread area by area through the field, early and accurate diagnosis of plant diseases in a part of a farm - which is provided by image processing techniques and machine vision systems – is very useful for timely and effective disease treatment which in turn leads to lower crop losses. Also, by using the site-specific chemical application technologies, the need for chemicals can be minimized, an important factor that can considerably reduce the costs.
