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
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
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.
H. Biabi; S. Abdanan Mehdizadeh; M. Salehi Salmi
Abstract
IntroductionThe automatic detection of plant diseases in early stages in large farms, in addition to increasing the quality of the final product, could prevent the occurrence of irreparable damage. To this end, accurate and timely diagnosis of farm conditions is of great importance. In order to facilitate ...
Read More
IntroductionThe automatic detection of plant diseases in early stages in large farms, in addition to increasing the quality of the final product, could prevent the occurrence of irreparable damage. To this end, accurate and timely diagnosis of farm conditions is of great importance. In order to facilitate production potential and prevent a significant decline in yield, disease diagnosis is necessary periodically throughout the whole life of the. On the other hand, early detection of the disease in its early stages of growth can also prevent the spread of diseases. One of the most common methods for diagnosing plant diseases is the use of visual methods, but this method is difficult to evaluate the performance of a number of parameters such as the effects of the environment, nutrients, and organisms and so on. Furthermore, the accuracy of repetitions is very much related to individual fatigue of inspector. Research on activities that have the ability to identify diseases at an early stage and prevent the spread of contagious diseases are of great importance. Therefore, the use of new applications and new detection technologies to protect can significantly reduce the risk of product loss. Therefore, the purpose of this research is to design and construct an intelligent control system that automatically detects the health of the lilium plant and to improve the plant's condition.Materials and MethodsSample collectionIn this study, 80 pots of four kilograms (including healthy and disease plants) were considered for plant growth in vegetative stage. The spring onions were grown in pots with 20 cm diameter and 30 cm height. Experiments were carried out in a greenhouse with a temperature of 27.15°C day/night and a relative humidity of 70-75%.Image processing In this research, the camera was placed at a constant distance of 50 cm from the flower to evaluate the stem and the leaves attached to it. The images were captured under the constant light conditions in the greenhouse during a specific hour of the day (10 to 12) every other day. The image was taken in RGB color space with a resolution of 1024 × 840 pixels, and after image transfer to the computer, image processing was performed using Matlab 2016a. After examining the plant image, 9 color channels (R, G, B, L, a, b, H, S, and V) were examined from three color spaces (RGB, Lab and HSV) and stem length to diagnosis of Botrytis elliptica disease.Feature selection and classification In this research, after improving the image and extracting the feature, the linguistic hedges method was used to select the features and the K-means clustering was applied in the N-division of the k-clustering specified by the user. In this method, each attribute was assigned to a cluster closer to the mean vector. This method continues until there was no significant change in the mean vectors between successive repetitions of the algorithm.Results and DiscussionAccording to the results of feature selection L leaf, L stem, a leaf, b leaf, H leaf, b stem, H stem, V leaf and stem length, were the best features. Moreover, the accuracy of diagnosis for the diseased and healthy plants were 96.42 and 100 percent, respectively, and the overall classification accuracy was 97.63 percent. Therefore, in general, it can be said that the proposed image processing method is desirable and acceptable in order to diagnose the disease. According to this, zhuang et al. (2017) used sparse representation (SR) classification and K-means clustering to identify leaf-based cucumber disease. In the proposed method, it has been shown that system could detect cucumber diseases with accuracy rate of 85.7%. Therefore, the proposed image processing technique seems to be able to diagnose the disease quickly and easily.ConclusionToday, in the modern agricultural systems, numerous computational methods have been designed to help farmers to control the proper growth of their products. However, there are still major problems with the rapid, accurate and classification of diseases in the early days of the disease. Therefore, the purpose of this study was to design, construct and evaluate a smart system based on image processing in order to identify and classify the leaf disease of the leaves of the lilium plant and remove it by spraying the contaminated parts. For this purpose, the linguistic hedges method was used to select the characteristics and k-means method to classify the infected plant from healthy. The results of the classification for the diseased and healthy plants were 96.42 and 100 percent, respectively, and the overall classification accuracy was 97.63 percent, which indicates the acceptable accuracy of the machine vision system in detecting the disease.
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.
A. Kohan; S. Minaei
Abstract
Several histogram equalization methods for enhancing the color images of Rosa Damascena flowers and some thresholding methods for segmentation of the flowers were examined. Images were taken outdoors at different times of day and light conditions. A factorial experiment in the form of a Completely Randomized ...
Read More
Several histogram equalization methods for enhancing the color images of Rosa Damascena flowers and some thresholding methods for segmentation of the flowers were examined. Images were taken outdoors at different times of day and light conditions. A factorial experiment in the form of a Completely Randomized Design with two factors of histogram equalization method at 8 levels and thresholding method at 15 levels, was implemented. Histogram equalization methods included: CHE, BBHE, BHEPL-D, DQHEPL, DSIHE, RMSHE, RSIHE, and no histogram equalization (NHE) as the control. Thresholding method levels were: Huang, Intermodes, Isodata, Li, maximum entropy, mean, minimum, moments, Otsu, percentile, Renyi’s entropy, Shanbhag, Yen, constant, and global basic thresholding method. The effect of these factors on the properties of the segmented images such as the Percentage of Incorrectly Segmented Area (PISA), Percentage of Overlapping Area (POA), Percentage of Undetected Area (PUA), and Percentage of Detected Flowers (PDF) was investigated. Results of histogram equalization analysis showed that DQHEPL and NHE have the statistically significant lowest PUA (11.13% and 8.32%, respectively), highest POA (89.35% and 92.07%, respectively), and highest PDF (61.88% and 64.94%, respectively). Thresholding methods had a significant effect on PISA, PUA, POA, and PDF. The highest PDF belonged to constant, minimum, and Intermodes (75.07%, 73.08% and 74.30%, respectively) They also had the lowest PISA (0.35%, 1.29%, and 1.85%, respectively) and PUA (33.72%, 23.09%, and 15.56%, respectively). These methods had the highest POA (80.73%, 76.70%, and 84.67%, respectively). Hence, they are suitable methods for segmentation of Rosa Damascena flowers in color images.
Design and Construction
H. Biabi; S. Abdanan Mehdizadeh; M. Nadafzadeh; M. Salehi Salmi
Abstract
Introduction Leaf color is usually used as a guide for assessments of nutrient status and plant health. Most of the existing methods that examined relationships between chlorophyll status and carotenoid of leaf color were developed for particular species. Different methods have been developed to measure ...
Read More
Introduction Leaf color is usually used as a guide for assessments of nutrient status and plant health. Most of the existing methods that examined relationships between chlorophyll status and carotenoid of leaf color were developed for particular species. Different methods have been developed to measure chlorophyll status and carotenoid. However, the high cost and difficulty to use have restricted their application, whereas the handheld chlorophyll meters such as the SPAD has become popular in the last decade for non-destructive measurement of chlorophyll content. SPAD meter readings have found to be related to the plant’s nutrition status, seed protein content, types of nodulation, and photosynthetic rates of leaves. Digital color (RGB) image analysis, another nondestructive technique is becoming increasingly popular with its potential in phenotyping various parameters of plant health status. The development of low-cost digital cameras that use charged-couple device (CCD) arrays to capture images offers an advantage of low-cost real-time monitoring process over optical sensor based SPAD meter. Gupta et al. (2012) estimated chlorophyll content, using simple leaf digital analysis procedure in parallel to a SPAD chlorophyll content meter. The chlorophyll content as determined by the SPAD meter was significantly correlated to the RGB values of leaf image analysis (RMSE = 3.97). The aim of this research is developing a new inexpensive, hand-held and easy-to-use technique for detection of chlorophyll and carotenoid content in plants based on leaf color. This method provides rapid analysis and data storage at minimal cost and does not require any technical or laboratory skills. Materials and Methods Sample collection In this research, 15 leaves were randomly selected from six types of plants (Shoeblackplant, Vitex, Spiderwort, Sacred fig, Vine and Lotus). Afterwards, the chlorophyll content of the leaf was measured in 3 different ways: 1) using a SPAD instrument; 2) using machine vision system (non-destructive method), and 3) laboratory test using a spectrophotometer. Chlorophyll and carotenoid content The chlorophyll content of the leaf was measured and recorded using SPAD chlorophyll meter (Hansatech, model CL-01, Japan) and spectrometer as explained by Dey et al. (2016). Furthermore, to measure the carotenoid content method described by Gitelson et al. (2006) was utilized. Image processing For estimation of chlorophyll using the image processing algorithm, sample images were taken using CCD (CASIO, model Exilim EX-ZR700, Japan) and transferred to the computer. The camera was mounted perpendicular to the horizontal plane at a fixed distance of 25 cm from the samples. In a consequence histogram of leaf, images were equalized and the average of each color channels from RGB, Lab, HSV, and I1I2I3 were extracted using Matlab 2016. Decision tree regression (DTR) algorithm To develop a regression model to predict chlorophyll and carotenoid content, two decision tree were constructed. The average of each color channels from RGB, Lab, HSV, and I1I2I3 become the predictor variables or feature vector and the real known chlorophyll and carotenoid content become the target variable or the target vector of each regression tree. To develop the regression models, dataset (90 observations) was split into training (60 observations) and test (30 observations) data. Results and Discussion According to the obtained results, a high correlation of 0.92 for chlorophyll and 0.85 for carotenoid was achieved, respectively, between the image processing method and the values measured by the spectrometer. Therefore, it can be said that the proposed image processing method has a desirable and acceptable performance for prediction of both chlorophyll content and carotenoid. The review points out a need for fast and precise leaf chlorophyll measurement technique. With this in mind, Dey et al. (2016) used image processing techniques to measure chlorophyll content. For the purpose of analysis of the proposed model, the model outcome was compared with the LEAF+ chlorophyll meter reading. Regression analysis proofed that there was a strong correlation between the proposed image processing technique and chlorophyll meter reading. Thus, it appears that the proposed image processing technique of leaf chlorophyll measurement will be a good alternative for measuring leaf chlorophyll rapidly and with ease. Conclusion In this research, collections of images from six divers plants (Shoeblackplant, Vitex, Spiderwort, Sacred fig, Vine and Lotus) were analyzed to predict chlorophyll and carotenoid content at different color spaces (RGB, Lab, HSV, and I1I2I3). Based on the results, it was shown that there were high correlations of 0.92 for chlorophyll content as well as 0.85 for carotenoid between the image processing method and the values measured by the spectrometer. Therefore, in general, it can be concluded that the proposed image processing method has a desirable and acceptable performance for prediction of chlorophyll content as well carotenoid.
S. M. Hosseini; A. A. Jafari
Abstract
Introduction Great areas of the orchards in the world are dedicated to cultivation of the grapevine. Normally grape vineyards are pruned twice a year. Among the operations of grape production, winter pruning of the bushes is the only operation that still has not been fully mechanized while it is known ...
Read More
Introduction Great areas of the orchards in the world are dedicated to cultivation of the grapevine. Normally grape vineyards are pruned twice a year. Among the operations of grape production, winter pruning of the bushes is the only operation that still has not been fully mechanized while it is known as the most laborious jobs in the farm. Some of the grape producing countries use various mechanical machines to prune the grapevines, but in most cases, these machines do not have a good performance. Therefore intelligent pruning machine seems to be necessary in this regard and this intelligent pruning machines can reduce the labor required to prune the vineyards. It this study in was attempted to develop an algorithm that uses image processing techniques to identify which parts of the grapevine should be cut. Stereo vision technique was used to obtain three dimensional images from the bare bushes whose leaves were fallen in autumn. Stereo vision systems are used to determine the depth from two images taken at the same time but from slightly different viewpoints using two cameras. Each pair of images of a common scene is related by a popular geometry, and corresponding points in the images pairs are constrained to lie on pairs of conjugate popular lines. Materials and Methods Photos were taken from gardens of the Research Center for Agriculture and Natural Resources of Fars province, Iran. At first, the distance between the plants and the cameras should be determined. The distance between the plants and cameras can be obtained by using the stereo vision techniques. Therefore, this method was used in this paper by two pictures taken from each plant with the left and right cameras. The algorithm was written in MATLAB. To facilitate the segmentation of the branches from the rows at the back, a blue plate with dimensions of 2×2 m2 were used at the background. After invoking the images, branches were segmented from the background to produce the binary image. Then, the plant distance from the cameras was calculated by using the stereo vision. In next stage, the main trunk and one year old branches were identified and branches with thicknesses less than 7 mm were removed from the image. To omit these branches consecutive dilation and erosion operations were applied with circular structures having radii of 2 and 4 pixels. Then, based on the branch diameter, one-year-old branches were detected and pruned through considering the pruning parameters. The branches were pruned so that only three buds were left on them. For this aim, the branches should be pruned to have a length of 15 cm. To truncate the branches to 15 cm, the length of the main stem was measured for each of the branches, and branches with length less than 15 cm were omitted from the images. Then the main skeleton of grapevine was determined. Using this skeleton, the attaching points of the branches as well as attachment points to the trunk were identified. Distance between the branches was maintained. At the last step, the cutting points on the branches were determined by labeling the removed branches at each step. Results and Discussion The results indicated that the color components in the texture of the branches could not be used to identify one year old branches and evaluation results of algorithm showed that the proposed algorithm had acceptable performance and in all photos, one year old branches were correctly identified and pruning point of the grapevines were correctly marked. Also among 254 cut off-points extracted from 20 images, just 7 pruning points were misdiagnosed. These results revealed that the accuracy of the algorithm was about 96.8 percent. Conclusion Based on the reasonable achievement of the algorithm it can be concluded that it is possible to use machine vision routines to determine the most suitable cut off points for pruning robots. By an intelligent pruning robot, the one year old branches are diagnosed properly and the cut off points of the plants are determined. This can reduce the required labor to perform winter pruning in vineyards which subsequently reduces the time required and the costs needed for pruning the vineyards.
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
Z. Abdolahzare; M. A. Asoodar; N. Kazemi; M. Rahnama; S. Abdanan Mehdizadeh
Abstract
Introduction: Since the application of pneumatic planters for seeds with different physical properties is growing, it is essential to evaluation the performance of these machines to improve the operating parameters under different pressures and forward speeds. To evaluate the performance of precision ...
Read More
Introduction: Since the application of pneumatic planters for seeds with different physical properties is growing, it is essential to evaluation the performance of these machines to improve the operating parameters under different pressures and forward speeds. To evaluate the performance of precision vacuum seeders numerous procedures of laboratory and field have been developed and their feed mechanism evaluation is of great importance. The use of instrumentation is essential in laboratory procedures. Many systems have been designed, using instrumentation, to be able to monitor seed falling trajectory and as a result, in those systems the precise place of falling seed in the seed bed could be determined. In this study, the uniformity of seed spacing of a seed drill was determined using of high speed camera with a frame rate of 480 frames s-1. So that, the uniformity of planting was statistically significant under the influence of the speed of seed metering rollers (Karayel et al., 2006). Singh et al. (2005) studied the effects of disk rotation speed, vacuum pressure and shape of seed entrance hole on planting spacing uniformity using uniformity indices under laboratory and field conditions. They reported miss index values were reduced as the pressure was increased but they were increased with increasing of the speed. The multiple indices on the other hand were low at higher speed but they were increased as the pressure was increased. Ground speed was affected by changes in engine speed and gear selection, both of which effect on amount of fan rotation speed for different pressures. The aim of this study was to identify and determine the effects of forward speed and optimum vacuum pressure amount of the pneumatic seeder.Materials and Methods: The pneumatic planter (Unissem) was mounted on a tractor (MF399) and passed over the soil bin. Thus, the acquired data would be more reliable and practical. To do so, the tractor was equipped with electronic devices for online measurement of various parameters, including: the actual forward speed, wheel sleep percent, drawbar pull, motor RPM, and fuel consumption. Wheel drive of the seed metering mechanism was equipped with Rotary Encoder model S48-8-0360ZT (TK1) to determine the seed disk rotation. For more precise vacuum pressure monitoring, a Vacuum Transmitter model BT 10-210 was used to measure relative pressure from 0 mbar to -1000 mbar. Investigation of seed falling trajectories was conducted using the AVI video acquisition system consisted of CCD (charge-coupled device) camera (Fuji F660EXR) capable of capturing images with a constant speed of 320 frames per second and a spatial resolution of 320×240 pixels. All data were transmitted to a data logger and displayed online on the PC's screen.For optimization of the factors affecting the performance of the pneumatic planter, the experiments were conducted with: two ranges of forward speeds [3 to 4 km h-1, and 6 to 8 km h-1; three levels of vacuum pressure [-2.5kPa, -3.5kPa and -4.5 kPa]; and two types of seed [cucumber and watermelon], keeping a three-factor factorial experimental design. The tests were replicated three times. The uniformity of seed spacing was measured with indicators described by kachman and smith (1995) which are defined as:I_miss=N_1/N×100 (1)I_mul=N_2/N×100 (2)I_qf=100-(I_mul+I_miss) (3)P=s_d/x_ref (4)Which for planting distance of 45 cm, N1 is number of spacing > 1.5Xref; N2 is number of spacing ≤ 0.5Xref and N is total number of measured spacings, Sd is standard deviation of the spacing more than half but not more than 1.5 times, the set spacings Xref, Imiss is the miss index, Imul is the multiple index, quality of feed index Iq is the percentage of spacings that are more than half but not more than 1.5 times, the set planting distance and P is error index.Results and Discussion: According to the studies on both watermelon and cucumber, the ‘quality of feed index’ value in forward speed rang of 6 to 8 km h-1 was less than one in forward speed rang of 3 to 4 km h-1. Also, the ‘error index’ value in forward speed rang 3 to 4 km h-1 was little rather than forward speed rang of 6 to 8 km h-1, but it was desirable.For watermelon and cucumber seeds, the ‘quality of feed index’ were the maximum with mean of 97% and 87% under vacuum pressures of -2.5 kPa and -4.5 km h-1, respectively and forward speed of 3 to 4 km h-1; so that for cucumber seed in the mention treatment, the ‘miss index’ was lowest with mean of zero.The ‘multiple index’ was highest with mean of 6% at 3 to 4 km h-1 forward speed and vacuum pressures of -4.5 for watermelon seed. Values of this index at both forward speed and three levels of vacuum pressures, for cucumber seed was more than watermelon seed.Miss index values were reduced as the pressure was increased but increased with increasing of speed. With lower vacuum pressure and at higher speeds, the metering disc did not get enough time to pick up seeds, resulting the higher miss indices. On the other hand, the multiple indices were low at higher speed but were increased as the pressure was increased (Panning et al. 2000; Zulin et al. 1991).Conclusions: It was observed that seed spacing uniformity was affected by both speed and pressure but not equally. Extracted regression models showed that the best uniformity of spacing for watermelon seed obtained at the rang of speed of 3 to 4 km/h and pressure of -3.5 kPa with a error in spacing of 7% in laboratory condition. Furthermore, in field condition the best uniformity of the seed space occurred at the pressure of -2.5 kPa and rang of speed of 6 to 8 km/h with a 9% error. Similarly, for cucumber seed results showed that the best uniformity obtained at the rang of speed of 3 to 4 km.h-1 and pressure of -4.5 kPa in laboratory condition, and at the low speed and pressure of -2.5 kPa in the field.
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.
A. Jafari Malekabadi; M. Khojastehpour; B. Emadi; M. R. Golzarian
Abstract
Introduction: Poisson ratio and modulus of elasticity are two fundamental properties of elastic and viscoelastic solids that use in solving all contact problems, including the calculation of stress, the contact surfaces and elastic deformation (Mohsenin, 1986; Gentle and Halsall, 1982).
There are many ...
Read More
Introduction: Poisson ratio and modulus of elasticity are two fundamental properties of elastic and viscoelastic solids that use in solving all contact problems, including the calculation of stress, the contact surfaces and elastic deformation (Mohsenin, 1986; Gentle and Halsall, 1982).
There are many published literature on Poisson ratio and elasticity modulus of fruit and vegetables. Shitanda et al. (2002) calculated Poisson ratio of rice by considering Boussinesq’s theory. They showed that the Poisson ratio is greater for shorter varieties. In another study, researchers used the instrumented bending beam to measure the lateral expansion of red beans. They were considered Poisson ratio as the ratio of transverse strain to the longitudinal strain (regardless of the geometry of the sample) and were calculated modulus of elasticity with Hertz theory for convex bodies (Kiani Deh Kiani et al., 2009). Cakir et al. (2002) was determined the Poisson ratio and elastic modulus of some onion varieties. They used a simple formula to determine the transverse strain that developed by Sitkei (1986) for prism-shaped rod, regardless of the geometry of the product.
Reviewed scientific literature shows that these parameters have not been studied according to the geometric shape of onions and was not used by a more accurate method, such as image processing to determine these parameters. The objective of this study was to evaluate the mechanical properties of two varieties of onions. Poisson ratio was determined with image processing. Considering shape of the onions and deformation value, and using Hertz’s theory with Poisson ratio, modulus of elasticity was calculated. The effects of loading directions (polar or equatorial), deformation value (5, 10 and 15 mm), loading speed (15 or 25 mm min-1) and onion varieties (Red and Yellow) on the modulus of elasticity and apparent Poisson’s ratio were examined.
Materials and Methods: The onions harvested in autumn, 20 days before conducting the tests. Onion samples kept at room temperature (21oC). Onions of each cultivar were randomly selected. Diameters of onion were measured with a digital vernier caliper. In each run, eight onions were randomly selected and the loading test and photography were done together and the average values reported.
All mechanical tests were performed using a Universal Testing Machine (UTM) (Model H5KS, Tinius Olsen Company) between two rigid plates. The loading was made with two constant speeds of 15 and 25 mm min-1. Deformation values were 5, 10 and 15 mm. The onions were loaded either axially or laterally until rupture point and photography were done together.
The initial and current onion diameters along the y and x axes obtained by using image processing and the strains were calculated. Having axially and laterally strains of the onions, the apparent Poisson's ratio was calculated using equation presented by Figura and Teixeira 2007; Kiani Deh Kiani et al., 2009; Pallottino et al., 2011; Kabas and Ozmerzi 2008; Gladyszewska and Ciupak 2009.
A factorial experiment based on a completely randomized design with 8 replications was applied. The significant differences of means were compared by using the Duncan’s multiple range test at 5% significant level. SPSS 20.0 software was used for data analysis.
Results and Discussion: According to the analysis of variance (Table 2), the effects of speed and displacement of loading was significant in 5% probability levels. In addition, interaction effect varieties × directions × speed along Y, varieties × directions, varieties × speed and directions × speed along X was significant in 1, 1, 5 and 5% probability levels, respectively. The average of the apparent Poisson ratio for Yellow onion was less than that obtained for the Red onion, because Red onions have softer texture than Yellow onions. Apparent Poisson ratio was obtained as 0.2623 to 0.4485 and 0.2423 to 0.4179 for Yellow and Red onions, respectively. With increasing deformation, apparent Poisson ratio increased.
Modulus of elasticity along X and Y
According to the analysis of variance (Table 2), the effects of speed and displacement of loading and directions × speed was significant in 1% probability levels. The average of the modulus of elasticity for Red onion was less than that obtained for the Yellow onion because Yellow onion has tougher and more powerful texture than Red onion. Modulus of elasticity were obtained as 2.032 to 5.449 and 1.829 to 5.311 MPa for Yellow and Red onions, respectively. The modulus of elasticity for lateral loading was less than that obtained for the axial loading. With increasing deformation, the modulus of elasticity decreased. The modulus of elasticity for lateral loading in loading speed 25 mm min-1 was less than that obtained for loading speed 15 mm min-1.
Conclusions: The results were summarized as below:
Loading speed, deformation value and their interaction effect were significant in different confidence levels for apparent Poisson's ratio and modulus of elasticity.
The compression force of Yellow onion was more than Red onion. Thus, it can be concluded that Yellow onions have more strength against the forces and loading.
The modulus of elasticity for lateral loading was less than that obtained for the axial loading. It is better to be considered for packaging of onions.
The modulus of elasticity for lateral loading in loading speed 25 mm min-1 was less than that obtained for loading speed 15 mm min-1.
With increasing deformation, the modulus of elasticity and apparent Poisson’s ratio decreased and increased, respectively.
I. Golpour; J. Amiri Parian; R. Amiri Chayjan; J. Khazaei
Abstract
Identification of rice cultivars is very important in modern agriculture. Texture properties could be used to identify of rice cultivars among of the various factors. The digital images processing can be used as a new approach to extract texture features. The objective of this research was to identify ...
Read More
Identification of rice cultivars is very important in modern agriculture. Texture properties could be used to identify of rice cultivars among of the various factors. The digital images processing can be used as a new approach to extract texture features. The objective of this research was to identify rice cultivars using of texture features with using image processing and back propagation artificial neural networks. To identify rice cultivars, five rice cultivars Fajr, Shiroodi, Neda, Tarom mahalli and Khazar were selected. Finally, 108 textural features were extracted from rice images using gray level co-occurrence matrix. Then cultivar identification was carried out using Back Propagation Artificial Neural Network. After evaluation of the network with one hidden layer using texture features, the highest classification accuracy for paddy cultivars, brown rice and white rice were obtained 92.2%, 97.8% and 98.9%, respectively. After evaluation of the network with two hidden layers, the average accuracy for classification of paddy cultivars was obtained to be 96.67%, for brown rice it was 97.78% and for white rice the classification accuracy was 98.88%. The highest mean classification accuracy acquired for paddy cultivars with 45 features was achieved to be 98.9%, for brown rice cultivars with 11 selected features it was 93.3% and it was 96.7% with 18 selected features for rice cultivars.
A. Moghimi; M. H. Aghkhani; M. R. Golzarian
Abstract
In recent years, automation in agricultural field has attracted more attention of researchers and greenhouse producers. The main reasons are to reduce the cost including labor cost and to reduce the hard working conditions in greenhouse. In present research, a vision system of harvesting robot was developed ...
Read More
In recent years, automation in agricultural field has attracted more attention of researchers and greenhouse producers. The main reasons are to reduce the cost including labor cost and to reduce the hard working conditions in greenhouse. In present research, a vision system of harvesting robot was developed for recognition of green sweet pepper on plant under natural light. The major challenge of this study was noticeable color similarity between sweet pepper and plant leaves. To overcome this challenge, a new texture index based on edge density approximation (EDA) has been defined and utilized in combination with color indices such as Hue, Saturation and excessive green index (EGI). Fifty images were captured from fifty sweet pepper plants to evaluate the algorithm. The algorithm could recognize 92 out of 107 (i. e., the detection accuracy of 86%) sweet peppers located within the workspace of robot. The error of system in recognition of background, mostly leaves, as a green sweet pepper, decreased 92.98% by using the new defined texture index in comparison with color analysis. This showed the importance of integration of texture with color features when used for recognizing sweet peppers. The main reasons of errors, besides color similarity, were waxy and rough surface of sweet pepper that cause higher reflectance and non-uniform lighting on surface, respectively.
Image Processing
S. Latifaltojar; A. A. Jafari; S. M. Nassiri; H. Sharirfi
Abstract
Crop yield estimation is one of the most important parameters for information and resources management in precision agriculture. This information is employed for optimizing the field inputs for successive cultivations. In the present study, the feasibility of sugar beet yield estimation by means of machine ...
Read More
Crop yield estimation is one of the most important parameters for information and resources management in precision agriculture. This information is employed for optimizing the field inputs for successive cultivations. In the present study, the feasibility of sugar beet yield estimation by means of machine vision was studied. For the field experiments stripped images were taken during the growth season with one month intervals. The image of horizontal view of plants canopy was prepared at the end of each month. At the end of growth season, beet roots were harvested and the correlation between the sugar beet canopy in each month of growth period and corresponding weight of the roots were investigated. Results showed that there was a strong correlation between the beet yield and green surface area of autumn cultivated sugar beets. The highest coefficient of determination was 0.85 at three months before harvest. In order to assess the accuracy of the final model, the second year of study was performed with the same methodology. The results depicted a strong relationship between the actual and estimated beet weights with R2=0.94. The model estimated beet yield with about 9 percent relative error. It is concluded that this method has appropriate potential for estimation of sugar beet yield based on band imaging prior to harvest
Image Processing
M. Jafarlou; R. Farrokhi Teimourlou
Abstract
Physical properties of agricultural products such as volume are the most important parameters influencing grading and packaging systems. They should be measured accurately as they are considered for any good system design. Image processing and neural network techniques are both non-destructive and useful ...
Read More
Physical properties of agricultural products such as volume are the most important parameters influencing grading and packaging systems. They should be measured accurately as they are considered for any good system design. Image processing and neural network techniques are both non-destructive and useful methods which are recently used for such purpose. In this study, the images of apples were captured from a constant distance and then were processed in MATLAB software and the edges of apple images were extracted. The interior area of apple image was divided into some thin trapezoidal elements perpendicular to longitudinal axis. Total volume of apple was estimated by the summation of incremental volumes of these elements revolved around the apple’s longitudinal axis. The picture of half cut apple was also captured in order to obtain the apple shape’s indentation volume, which was subtracted from the previously estimated total volume of apple. The real volume of apples was measured using water displacement method and the relation between the real volume and estimated volume was obtained. The t-test and Bland-Altman indicated that the difference between the real volume and the estimated volume was not significantly different (p>0.05) i.e. the mean difference was 1.52 cm3 and the accuracy of measurement was 92%. Utilizing neural network with input variables of dimension and mass has increased the accuracy up to 97% and the difference between the mean of volumes decreased to 0.7 cm3.
