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. Heidari; J. Amiri Parian
Abstract
Repetitive and dangerous tasks such as harvesting and spraying have made robots usable in the greenhouses. The mechanical structure and navigation algorithm are two important parameters in the design and fabrication of mobile greenhouse robots. In this study, a four- wheel differential steering mobile ...
Read More
Repetitive and dangerous tasks such as harvesting and spraying have made robots usable in the greenhouses. The mechanical structure and navigation algorithm are two important parameters in the design and fabrication of mobile greenhouse robots. In this study, a four- wheel differential steering mobile robot was designed and constructed to act as a greenhouse robot. Then, the navigation of the robot at different levels and actual greenhouses was evaluated. The robot navigation algorithm was based on the path learning, so that the route was stored in the robot memory using a remote control based on the pulses transmitted from the wheels encoders; then, the robot automatically traversed the path. Robot navigation accuracy was tested at different surfaces (ceramics, concrete, dense soil and loose soil) in a straight path 20 meters long and a square path, 4×4 m. Then, robot navigation accuracy was investigated in a greenhouse. Robot movement deviation value was calculated using root mean square error (RMSE) and standard deviation (SD). The results showed that the RMSE of deviation of autonomous method from manual control method in the straight path to the length of 20 meters in ceramic, concrete, dense soil and loose soil were 4.3, 2.8, 4.6 and 8 cm, and in the 4×4 m square route were 6.6, 5.5, 13.1 and 47.1 cm, respectively.
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.
S. Sadeghzade Namavar; J. Amiri Parian; R. Amiri Chayjan
Abstract
Introduction The artichoke is part of the foods from the vegetable group that provide important nutrients like vitamin A and C, potassium and fiber which used as a food and medicine. In the pharmaceutical sector, dried extracts are used in the preparation of pills and capsules. Dried extracts can be ...
Read More
Introduction The artichoke is part of the foods from the vegetable group that provide important nutrients like vitamin A and C, potassium and fiber which used as a food and medicine. In the pharmaceutical sector, dried extracts are used in the preparation of pills and capsules. Dried extracts can be prepared from the dehydration of a concentrated extractive solution from herbal materials (leaves, roots, seeds, etc.), resulting in a dried powder. The spray drying is widely used in the preparation of dried powders from extracts of medicinal plants, fruit pulps. One of the newly developed spray drying techniques is an ultrasonic vacuum method, which strengths of spray drying by incorporation of ultrasonic atomizer and vacuum chamber. Nowadays, image processing has been applied to food images, as acquired by different microscopic systems, to obtain numerical data about the morphology and microstructure of the analyzed foods. For this purpose, microscopy and image processing techniques could be considered as proper tools to evaluate qualitatively and quantitatively the food microstructure, making possible to carry out numerical correlations between microstructure data, as obtained from the images, and the textural properties of food powders. The textural characteristics of the obtained dried powders are determined by means of a perfect detection by scanning electron microscopy (SEM) pictures, and analyzed with a statistical approach for image texture studies, which calls the gray level co-occurrence matrix (GLCM) technique. The object of this study was to illustrate the application of image processing to the study of texture properties from extract powder using GLCM texture analysis and some vacuum spray dryer conditions effect on the texture features of mass particles and single particle SEM images. Materials and Methods After preparing water extract solution from artichoke leaves, extracts were dried under four conditions of vacuum spray drying (according to Table 1). To study the texture of the obtained dried extract powders, different representative features are extracted from the GLCM matrix. The angular second moment (ASM), which is defined as a measure of the homogeneity of the image, the contrast parameter (CT), which represents the amount of local variations given by differences in the gray values in the image. The correlation value (CR), which is a measure of gray tone linear dependencies in the image depending on the direction of the measure (different θs). The inverse difference moment value (IDM), which, similar to ASM, quantifies the homogeneity of the image, however, using a different equation, the entropy parameter (ET), which is a measure that is inversely related to the order given by the gray tones in the image. Rangefilt and stdfilt calculates the local range and local standard deviation of an image respectively. Entropyfilt calculates the local entropy of a grayscale image also. Parameters (ASM, CT, CR and IDM were analyzed in four directions (0º, 45º, 90º, and 135º). Results and Discussion The results of analysis of variance showed that, the difference between the textural features of a single particle and mass particles in four different conditions vacuum spray dryer was significant statistically. Texture analysis was demonstrated that larger ASM, CR, and IDM values indicate less roughness, whereas larger CT and ET values indicate more roughness. At lower inlet temperature and higher vacuum pressure, water diffusion in the material to be slower and allowing the deformation process in the particles to be more pronounced. Consequently, it was possible to observe that generated smaller particles are rougher and less spherical. When the concentration is increased, due to the constant concentration of the additive, the ratio of excipient (lactose) to extraction decreased, as a result were formed a greater number of particles with rougher surfaces. According to these conditions, the values of CT, ET, rangefilt and stdfilt were larger while ASM, CR, and IDM values were smaller. By analyzing the effect of the angle on the oriented textural characteristics, the contrast and correlation parameter were maximum at the angles of 45 and 135 degrees and 0 and 90 degrees respectively. Conclusion Image processing could be auxiliary tools for understanding and characterizing complex systems such as food and biological materials. In this study imaging-based technique was developed to evaluate the texture properties of artichoke leaf extract powder at different conditions of vacuum spray drying. The use of higher temperatures and lower vacuum pressures contributed to faster evaporation rate and production of smoother and larger particles, thereby increasing ASM, CR, and IDM values and reducing CT, ET, Rangefilt and stdfilt. Furthermore, the contrast and entropy parameters showed inverse trends in comparison with correlation, energy and homogeneity. Decrease of solution concentration resulted in the more presence of lactose in the composition of extract/excipient improves the textural properties of powders. The direction parameter had also affected on GLCM textural features. Two oriented textural characteristics (contrast and correlation) also showed significant differences with respect to the nature of particle texture in different directions of measurement. The obtained data extracted from image analysis may provide valuable information to understand the role of structure with respect to product functionality.
E. Chavoshi; J. Amiri Parian; B. Jabbari
Abstract
Introduction: Development of science in various fields has caused change in the methods to determine geographical location. Precision farming involves new technology that provides the opportunity for farmers to change in factors such as nutrients, soil moisture available to plants, soil physical and ...
Read More
Introduction: Development of science in various fields has caused change in the methods to determine geographical location. Precision farming involves new technology that provides the opportunity for farmers to change in factors such as nutrients, soil moisture available to plants, soil physical and chemical characteristics and other factors with the spatial resolution of less than a centimeter to several meters to monitor and evaluate. GPS receivers based on precision farming operations specified accuracies are used in the following areas: 1) monitoring of crop and soil sampling (less than one meter accuracy) 2) use of fertilizer, pesticide and seed work (less than half a meter accuracy) 3) Transplantation and row cultivation (precision of less than 4 cm) (Perez et al., 2011). In one application of GPS in agriculture, route guidance precision farming tractors in the fields was designed to reduce the transmission error that deviate from the path specified in the range of 50 to 300 mm driver informed and improved way to display (Perez et al., 2011). In another study, the system automatically guidance, based on RTK-GPS technology, precision tillage operations was used between and within the rows very close to the drip irrigation pipe and without damage to their crops at a distance of 50 mm (Abidine et al., 2004). In another study, to compare the accuracy and precision of the receivers, 5 different models of Trimble Mark GPS devices from 15 stations were mapped, the results indicated that minimum error was related to Geo XT model with an accuracy of 91 cm and maximum error was related to Pharos model with an accuracy of 5.62 m (Kindra et al., 2006).
Due to the increasing use of GPS receivers in agriculture as well as the lack of trust on the real accuracy and precision of receivers, this study aimed to compare the positioning accuracy and precision of three commonly used GPS receivers models used to specify receivers with the lowest error for precision farming operations as well as the efficiency of the work done in different situations.
Materials and Methods: In this study, three commonly used GPS models belong to GARMIN CO. were selected for comparison. This company is the world biggest manufacturer of GPS device. Three models include eTrex VISTA, MAP 60 csx and MAP 78s that in recent years have been the most widely used receivers in precision agriculture (Figure 1, Table 1). To assess the accuracy and precision of the receivers, 9 recording stations were selected in a field (20×20 m2) and detailed mapping by the odolite camera under high precision compass networks and regular conditions (figure 2) was identified. To reduce the error of multi-path, a relatively open and unobstructed place in the Abbas Abad field of Bu-Ali Sina University were considered. This study was conducted in a Completely Randomized Design (CRD) with factorial analysis to examine three factors, at three levels, each in three replication including weather conditions (clear, partially cloudy and full cloudy sky), time of day (9 am, 12 am and 4 pm) and three different models of receiver (MAP 60 csx, eTrex VISTA and MAP 78s), in 9 local stations. Difference of deviation value at each station with the mean value of latitude and longitude recorded at same station was used to precision calculate on (equation 1) and the difference of deviation value at each station with a deviation of the actual position latitude and longitude of the same station was used to calculate the accuracy (equation 2). The base station position (No.1) was determined with an accurately large-scale map. Then, the positions of other stations were defined with camera and compass in exact rectangular grid by underlying base station. Mean error for each station using equation (3) and the precision and accuracy and the definitions of each receiver was calculated.
Results and Discussion: To display the geographical distribution stations and the registered location data for GPS devices ArcView software (v3.3) was used (Fig.3). The real location of stations and registered by each receiver position has been determined. Information recorded in Map Source software, including all longitude and latitudes registered for each station and receiver were transferred to Excel Software (2007). Table 2 shows the mean precision values recorded in each weather conditions. The results obtained by equation 1 (the mean error at each station) showed that the GPS MAP 78s model has the lowest error of 91 cm, VISTA eTrex model has a maximum error of 4.7 meters and MAP 60 csx model has mean error of about 2.64 meters. The analysis of variance of models and weather conditions and the time of day with the interactions between factors have been shown in Table 3. Results showed that there is significant difference (0.01 <P value) between models, but there is no significant difference between the date and time positioning precision of different receivers models. Investigating of the interactions between the receiver models and the weather conditions showed no significant effect of them and the interaction between the receiver models and the measured time difference is not significant. These results showed that weather conditions and time of day is the same effect on positioning precision of GPS receivers used in this research. These results were consistent with the study of Jose and colleagues (Jose et al., 2006). The mean Comparison test of LSD (at 5% level) for the accuracy and precision of the models showed the significant difference for all models (Table 4). Figures 4 and 5 respectively show the accuracy and precision of three models of GPS receiver at different times of day and different weather conditions.
Conclusions: Effect of daylight hours on positioning precision was very low; also the effect of different weather conditions may reduce the accuracy of GPS positioning to size of few centimeters. Overall, the results indicated that between the three factors include the models, the effects of weather and time only receiver models had significant effect in precision. The lowest error between the models was belonged to MAP 78s (91 cm) and the maximum error was belonged to eTrex VISTA model with the 4.7 m. In addition, results of this study showed that the correct application of GPS receivers in different conditions and select of appropriate receiver can be reduced positioning error considerably. According to the result the MAP 78s GPS receiver could be used for precision farming operations in the range of 1 to 3 meter such as crop monitoring and soil sampling and the other receivers (eTrex VISTA and MAP 60 csx) could be used in operations that require less precision (range of 3 to 5 meters).
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.
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.
