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.
V. Rasooli Sharabiani; O. Farhangi; E. Taghinezhad
Abstract
Introduction Nowadays the packaging of a product is considered as a symbol of its quality and has a direct effect on its consumer-satisfaction and sales. The visual inspection method is much slower and more error-prone than that of automated method which is used for mass production. Also, this method ...
Read More
Introduction Nowadays the packaging of a product is considered as a symbol of its quality and has a direct effect on its consumer-satisfaction and sales. The visual inspection method is much slower and more error-prone than that of automated method which is used for mass production. Also, this method has other problems such as high labor cost, fatigue, low accuracy, and inconsistency due to various environmental conditions such as lighting, or lack of concentration as well as lack of standards and skilled worker. Machine vision has different applications in the industry. In the packaging of liquid such as cooking oils and different beverages (mineral water, soft drinks, fruit juices ...) that liquid can leak out. So, inspecting cap defects, seal ring defects and liquid level are urgent. Also, label placement plays an important role in customer satisfaction. Machine vision can be able to detect these defects; therefor its application will be effective and useful. So, the advantages of machine vision are non-destructive, accurate, and consistent. Researchers have been used the machine vision system for different area including inspection of surface and structural flaw inspection; steel strips and pharmaceutical tablets. Also, machine vision was used for online control of grading and separation of different agricultural products, such as kiwi, pomegranate, dates, cucumber, almonds, potatoes, tomato and peach. The aim of this research was to manufacture and application a system based on machine vision for inspection and classification of defects in bottles on production lines (case study: soft drink). Sample quality was included of three defects: cap defaults, liquid level and label placement. Materials and Methods 300cc Coca Cola bottles were used as samples for this research. The research was performed to inspect the common defects, including of the cap defaults, liquid level and label placement. In this research, a bottle classification system was designed and developed which it consists of hardware and a software unit. The hardware includes of a conveyor belt, a power system and a power transmission unit, light source, a digital camera, a mechanical ejector and a computer. In this project Lab view 2011 software was used. In this online system, decision was done based on Boolean logic and the defected bottles were separated from the normal ones. For image acquisition and algorithm design the different steps were followed: Vision acquisition, image processing and programming. Clamp (Rake) function was used for inspection of liquid level. It calculated the maximum distance between the cap and liquid level and its result was compared to the edge strength and threshold level. Inspection of cap defaults and label placement was performed using pattern matching and edge detection algorithm, respectively. The appropriate time of ejector must be calculated to take defective samples out of the production line. Results and Discussion Research results were reported at four parts including of cap defects, liquid level and label placement inspection furthermore the combination of all three groups. To find of inspection accuracy, it was repeated 100 times for each default. Accuracy of inspection of the cap, label placement and liquid level were earned as 95, 90 and 100%, respectively. The average accuracy of system was 95.6%. With regard to the conveyor belt’s speed (20cm s-1) and the distance (10cm) between the bottles, the required time to inspect each bottle was 500ms. So, program’s performance was acceptable according to process time of 150-250ms. Finally, the operational capacity of the system was 7200 bottles per hour. These findings were similar to results reported by other researchers. They reported the accuracy of 97 and 90.61% for beer bottles inspection and tomatoes separating, respectively. Conclusion Average of total accuracy for this system was obtained as 95.6%. It separately was 100, 95 and 92% for inspection of liquid level, cap, and label placement, respectively. The highest and lowest accuracy were for inspection of liquid level and label placement. So, performance of the algorithm was suitable for use on production lines. Also, it will be applicable to liquid packaging in the food industry, chemical industry and so on.
S. Sabzi; Y. Abbaspour Gilandeh; H. Javadikia
Abstract
Introduction With increase in world population, one of the approaches to provide food is using site-specific management system or so-called precision farming. In this management system, management of crop production inputs such as fertilizers, lime, herbicides, seed, etc. is done based on farm location ...
Read More
Introduction With increase in world population, one of the approaches to provide food is using site-specific management system or so-called precision farming. In this management system, management of crop production inputs such as fertilizers, lime, herbicides, seed, etc. is done based on farm location features, with the aim of reducing waste, increasing revenues and maintaining environmental quality. Precision farming involves various aspects and is applicable on farm fields at all stages of tillage, planting, and harvesting. Today, in line with precision farming purposes, and to control weeds, pests, and diseases, all the efforts of specialists in precision farming is to reduce the amount of chemical substances in products. Although herbicides improve the quality and quantity of agricultural production, the possibility of applying inappropriately and unreasonably is very high. If the dose is too low, weed control is not performed correctly. Otherwise, If the dosage is too high, herbicides can be toxic for crops, can be transferred to soil and stay in it for a long time, and can penetrate to groundwater. By applying herbicides to variable rate, the potential for significant cost savings and reduced environmental damage to the products and environment will be possible. It is evident that in large-scale modern agriculture, individual management of each plant without using some advanced technologies is not possible. using machine vision systems is one of precision farming techniques to identify weeds. This study aimed to detect three plant such as Centaurea depressa M.B, Malvaneglecta and Potato plant using machine vision system. Materials and Methods In order to train algorithm of designed machine vision system, a platform that moved with the speed of 10.34 was used for shooting of Marfona potato fields. This platform was consisted of a chassis, camera (DFK23GM021,CMOS, 120 f/s, Made in Germany), and a processor system equipped with Matlab 2015 version. The video camera was installed in 60-centimeter height above the ground level. Therefore, all plants in the camera field of view (whether on the crops row or between the rows) were analyzed. This study conducted on 4 hectares of potato fields in Kermanshah–Iran (longitude: 7.03 E; latitude: 4.22 N). The most suitable color space for segmentation plants was HSV color space and most suitable channel of applying threshold was the H channel. In this study, features in two areas of color features, texture features based on gray co-occurrence matrix were extracted. Ultimately, 126 color features and 80 texture features were extracted from each object. In final six features among 206 features were selected. Results and Discussion Among 206 extracted features, six effective features including the additional second component of the YCbCr color space, green index minus blue in RGB color space, sum entropy in the neighborhood of 45 degree, diagonal moment in the neighborhood of 0 degree, entropy in the neighborhood of 45 degree, additional third component index in CMY color space were selected using hybrid ANN-PSO. This means that, two set features have the same effect over plants. The result shows that hybrid ANN-SAGA classified Centaurea depressa M.B, Malvaneglecta and Potato plant with 99.61% accuracy. This accuracy is high and this meant that 1. These plants have different 6 selected features, 2. The classifier is very powerful to classify. Conclusion 1. Plants with similar features make the classification process complicated and less accurate. 2. The presence of shadow on the plants’ leaves reduces the accuracy of the classification.
Image Processing
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.
Image Processing
H. R. Ahmadi; J. Amiri Parian
Abstract
Within the last few years, a new tendency has been created towards robotic harvesting of oranges and some of citrus fruits. The first step in robotic harvesting is accurate recognition and positioning of fruits. Detection through image processing by color cameras and computer is currently the most common ...
Read More
Within the last few years, a new tendency has been created towards robotic harvesting of oranges and some of citrus fruits. The first step in robotic harvesting is accurate recognition and positioning of fruits. Detection through image processing by color cameras and computer is currently the most common method. Obviously, a harvesting robot faces with natural conditions and, therefore, detection must be done in various light conditions and environments. In this study, it was attempted to provide a suitable algorithm for recognizing the orange fruits on tree. In order to evaluate the proposed algorithm, 500 images were taken in different conditions of canopy, lighting and the distance to the tree. The algorithm included sub-routines for optimization, segmentation, size filtering, separation of fruits based on lighting density method and coordinates determination. In this study, MLP neural network (with 3 hidden layers) was used for segmentation that was found to be successful with an accuracy of 88.2% in correct detection. As there exist a high percentage of the clustered oranges in images, any algorithm aiming to detect oranges on the trees successfully should offer a solution to separate these oranges first. A new method based on the light and shade density method was applied and evaluated in this research. Finally, the accuracies for differentiation and recognition were obtained to be 89.5% and 88.2%, respectively.
Design and Construction
R. Loni; M. Loghavi
Abstract
Farmers are now more interested in application of weed control methods and tools with less environmental side effects. Flame weeding using propane gas is an approach with almost no any chemical residue on the soil and plant surfaces or underground water. In this research, a flame weeding machine with ...
Read More
Farmers are now more interested in application of weed control methods and tools with less environmental side effects. Flame weeding using propane gas is an approach with almost no any chemical residue on the soil and plant surfaces or underground water. In this research, a flame weeding machine with the ability of uniform and also discrete flaming was developed and evaluated in laboratory and field scales. In this apparatus, machine vision technology successfully discriminates between soil and weeds (plants grown in between the corn rows are considered as weeds) under natural illumination. In the laboratory tests, the effect of three forward speeds (0.5, 0.7 and 0.9 m s-1) on flam leading or lagging was investigated. The feasibility of using this technology for site-specific weed control of a corn field in comparison with conventional continuous flaming was investigated. The field trials were conducted with both continuous and discrete flaming approaches. The system performance and weed response to flaming treatments were evaluated by measuring the fuel consumption, counting the number of and weighting the survived and dead weeds one and three days after each flaming treatment. The results of laboratory tests showed that the effect of forward speed on system accuracy was significant and the system performance was more accurate at forward speeds of 0.5 and 0.7 m s-1 than 0.9 m s-1. According to the field experiments, continuous and discrete flaming methods exhibited similar results in eradication of weeds (both number and weight-based), while the fuel consumption of the discrete flaming was lower than the continuous one. The results also showed that discrete flaming by employing machine vision technology could be an efficient substitute for continuous flaming due to its lower fuel consumption and potential reduction of air pollution as well as other benefits of flame weeding.
