Estimation of Soil Surface Roughness Using Stereo Vision Approach.

Soil roughness is one of the most challenging issues in the agricultural domain and plays a crucial role in soil quality. The objective of this research was to develop a computerized method based on stereo vision technique to estimate the roughness formed on the agricultural soils. Additionally, soil till quality was investigated by analyzing the height of plow layers. An image dataset was provided in the real conditions of the field. For determining the soil surface roughness, the elevation of clods obtained from tillage operations was computed using a depth map. This map was obtained by extracting and matching corresponding keypoints as super pixels of images. Regression equations and coefficients of determination between the measured and estimated values indicate that the proposed method has a strong potential for the estimation of soil shallow roughness as an important physical parameter in tillage operations. In addition, peak fitting of tilled layers was applied to the height profile to evaluate the till quality. The results of this suggest that the peak fitting is an effective method of judging tillage quality in the fields.

Development and Laboratory Evaluation of an Online Controlling Algorithm for Precision Tillage.

Soil compaction management relies on costly annual deep tillage. Variable-depth tillage or site-specific tillage modifies the physical properties of the soil at the required zones for the growth of crops. In this study, a depth control system was designed for the subsoiler of the tillage at various depths. For this purpose, an algorithm was written to investigate the subsoiler location and soil compaction. A program was also developed to implement this algorithm using Kinco Builder Software to control the subsoiler depth, which was evaluated on the experimental platform. In this study, four compression sensors were used at a distance of 10 cm up to a depth of 40 cm on the blade mounted at the front of the tractor. The data of these sensors were used as the input and compared with the pressure baseline limit (2.07 MPa), and with the priority to select the greater depth, the depth of subsoiler was determined. At all three modes of sensor activation (single, collective, and combined), this system was able to operate the hydraulic system of the tractor and place the subsoiler at the desired depth through the use of the position sensors.

The Quality of Infrared Rotary Dried Terebinth (Pistacia atlantica L.)-Optimization and Prediction Approach Using Response Surface Methodology.

Most agricultural products are harvested with a moisture content that is not suitable for storage. Therefore, the products are subjected to a drying process to prevent spoilage. This study evaluates an infrared rotary dryer (IRRD) with three levels of infrared power (250, 500, and 750 W) and three levels of rotation speed (5, 10, and 15 rpm) to dry terebinth. Response surface methodology (RSM) was used to illustrate and optimize the interaction between the independent variables (infrared power and rotation speed) and the response variables (drying time, moisture diffusivity, shrinkage, color change, rehydration rate, total phenolic content, and antioxidant activity). As infrared power and rotation speed increased, drying time, rehydration rate, antioxidant activity, and total phenolic content decreased, while the other parameters were increased. According to the results, the optimum drying conditions of terebinth were determined in the IRRD at an infrared power of 250 W and drum rotation speed of 5 rpm. The optimum values of the response variables were 49.5 min for drying time, 8.27 × 10-9 m2/s for effective moisture diffusivity, 2.26 for lightness, 21.60 for total color changes, 34.75% for shrinkage, 2.4 for rehydration rate, 124.76 mg GAE/g d.m. for total phenolic content and 81% for antioxidant activity.

Response Surface Methodology Approach for Predicting Convective/Infrared Drying, Quality, Bioactive and Vitamin C Characteristics of Pumpkin Slices.

In this research, a convective/infrared (CV/IR) dryer was used to dry pumpkin slices. For optimization of the drying conditions, the influence of three levels of independent variables including air temperature (40, 55, and 70 °C), air velocity (0.5, 1, and 1.5 m/s), and IR power (250, 500, and 750 W) were assessed by response surface method (RSM) through a face-centered central composite design. Analysis of variance (non-fitting factor and R2 value) was employed to determine the desirability of the model. Response surfaces and diagrams were also utilized to show the interactive influence of the independent variables with the response variables (drying time, energy consumption, shrinkage, total color variation, rehydration ratio, total phenol, antioxidant, and vitamin C contents). According to the results, optimal drying conditions involved a temperature of 70 °C, air velocity of 0.69 m/s, and IR power of 750 W. At the mentioned conditions, response variables of drying time, energy consumption, shrinkage, color, rehydration ratio, total phenol, antioxidant, and vitamin C contents were 72.53 min, 24.52 MJ/kg, 23%, 14.74, 4.97, 617.97 mg GA/100 g dw, 81.57%, and 4.02 mg/g dw, with a confidence level of 0.948, respectively.

Combined Hot Air, Microwave, and Infrared Drying of Hawthorn Fruit: Effects of Ultrasonic Pretreatment on Drying Time, Energy, Qualitative, and Bioactive Compounds' Properties.

The present study aimed to examine the effect of ultrasonic pretreatment and hot air, microwave-hot-air, infrared-hot air, and freeze-drying on the drying time, specific energy (SE), qualitative properties (i.e., color, shrinkage, and rehydration ratio), and bioactive compounds' properties (i.e., antioxidant activity, phenolic, and flavonoid contents) of hawthorn fruit. Drying of hawthorn was conducted from 45 min for the ultrasonic + microwave-hot-air drying to 1280 min for the freeze-drying method. The lowest amount of SE was obtained using the ultrasonic-microwave-hot-air drying method, which was 47.57 MJ/kg. The lowest values in color changes (12.25) and shrinkage (17.21%) were recorded for the freeze-drying method, while the highest amounts for these traits were 45.57% and 66.75% in the HA drying, respectively. In general, the use of different drying methods reduces the antioxidant capacity (AC), total phenolic content (TPC), and total flavonoid content (TFC) during processing compared to fresh samples. The highest values for AC, TPC, TFC, and the rehydration ratio were 30.69%, 73.07 mg-GAE/gdw, 65.93 mg-QE/gdw, and 2.02 for the freeze-drying method, respectively.

Detection of fraud in ginger powder using an automatic sorting system based on image processing technique and deep learning.

Ginger is a well-known product in the food and pharmaceutical industries. Ginger is one of the spices which are adulterated for economic gain. The lack of marketability of grade 3 chickpeas (small and broken chickpeas) and their very low price have made them a good choice to be mixed with ginger in powder form and sold in the market. Demand for non-destructive methods of measuring food quality, such as machine vision and the growing need for food and spices, were the main motives to conduct this study. This study classified ginger powder images to detect fraud by improving convolutional neural networks (CNN) through a gated pooling function. The main approach to improving CNN is to use a pooling function that combines average pooling and max pooling. The Batch normalization (BN) technique is used in CNN to improve classification results. We show empirically that the combining operation used increases the accuracy of ginger powder classification compared to the baseline pooling method. For this purpose, 3360 image samples of ginger powder were prepared in 7 categories (pure ginger powder, chickpea powder, 10%, 20%, 30%, 40%, and 50% fraud in ginger powder). Moreover, MLP, Fuzzy, SVM, GBT, and EDT algorithms were used to compare the proposed CNN results with other classifiers. The results showed that using batch normalization based on gated pooling, the proposed CNN was able to grade the images of ginger powder with 99.70% accuracy compared to other classifiers. Therefore, it can be said that the CNN method and image processing technique effectively increase marketability, prevent ginger powder fraud, and promote traditional methods of ginger powder fraud detection.

A novel method based on machine vision system and deep learning to detect fraud in turmeric powder.

Assessing the quality of food and spices is particularly important in ensuring proper human nutrition. The use of computer vision method as a non-destructive technique in measuring the quality of food and spices has always been taken into consideration by researchers. Due to the high nutritional value of turmeric among the spices as well as the fraudulent motives to gain economic profit from the selling of this product, its quality assessment is very important. The lack of marketability of grade 3 chickpeas (small and broken chickpeas) and their very low price have made them a good choice to be mixed with turmeric in powder form and sold in the market. In this study, an improved convolutional neural network (CNN) was used to classify turmeric powder images to detect fraud. CNN was improved through the use of gated pooling functions. We also show with a combined approach based on the integration of average pooling and max pooling that the accuracy and performance of the proposed CNN has increased. In this study, 6240 image samples were prepared in 13 categories (pure turmeric powder, chickpea powder, chickpea powder mixed with food coloring, 10, 20, 30, 40 and 50% fraud in turmeric). In the preprocessing step, unwanted parts of the image were removed. The data augmentation (DA) was used to reduce the overfitting problem on CNN. Also in this research, MLP, Fuzzy, SVM, GBT and EDT algorithms were used to compare the proposed CNN results with other classifiers. The results showed that prevention of the overfitting problem using gated pooling, the proposed CNN was able to grade the images of turmeric powder with 99.36% accuracy compared to other classifiers. The results of this study also showed that computer vision, especially when used with deep learning (DL), can be a valuable method in evaluating the quality and detecting fraud in turmeric powder.

An automatic visible-range video weed detection, segmentation and classification prototype in potato field.

Weeds might be defined as destructive plants that grow and compete with agricultural crops in order to achieve water and nutrients. Uniform spray of herbicides is nowadays a common cause in crops poisoning, environment pollution and high cost of herbicide consumption. Site-specific spraying is a possible solution for the problems that occur with uniform spray in fields. For this reason, a machine vision prototype is proposed in this study based on video processing and meta-heuristic classifiers for online identification and classification of Marfona potato plant (Solanum tuberosum) and 4299 samples from five weed plant varieties: Malva neglecta (mallow), Portulaca oleracea (purslane), Chenopodium album L (lamb's quarters), Secale cereale L (rye) and Xanthium strumarium (coklebur). In order to properly train the machine vision system, various videos taken from two Marfona potato fields within a surface of six hectares are used. After extraction of texture features based on the gray level co-occurrence matrix (GLCM), color features, spectral descriptors of texture, moment invariants and shape features, six effective discriminant features were selected: the standard deviation of saturation (S) component in HSV color space, difference of first and seventh moment invariants, mean value of hue component (H) in HSI color space, area to length ratio, average blue-difference chrominance (Cb) component in YCbCr color space and standard deviation of in-phase (I) component in YIQ color space. Classification results show a high accuracy of 98% correct classification rate (CCR) over the test set, being able to properly identify potato plant from previously mentioned five different weed varieties. Finally, the machine vision prototype was tested in field under real conditions and was able to properly detect, segment and classify weed from potato plant at a speed of up to 0.15 m/s.

Prediction kinetic, energy and exergy of quince under hot air dryer using ANNs and ANFIS.

This study aimed to predict the drying kinetics, energy utilization (Eu ), energy utilization ratio (EUR), exergy loss, and exergy efficiency of quince slice in a hot air (HA) dryer using artificial neural networks and ANFIS. The experiments were performed at air temperatures of 50, 60, and 70°C and air velocities of 0.6, 1.2, and 1.8 m/s. The thermal parameters were determined using thermodynamic relations. Increasing air temperature and air velocity increased the effective moisture diffusivity (Deff ), Eu , EUR, exergy efficiency, and exergy loss. The value of the Deff was varied from 4.19 × 10-10 to 1.18 × 10-9 m2/s. The highest value Eu , EUR, and exergy loss and exergy efficiency were calculated 0.0694 kJ/s, 0.882, 0.044 kJ/s, and 0.879, respectively. Midilli et al. model, ANNs, and ANFIS model, with a determination coefficient (R 2) of .9992, .9993, and .9997, provided the best performance for predicting the moisture ratio of quince fruit. Also, the ANFIS model, in comparison with the artificial neural networks model, was better able to predict Eu , EUR, exergy efficiency, and exergy loss, with R 2 of .9989, .9988, .9986, and .9978, respectively.

Weed Classification for Site-Specific Weed Management Using an Automated Stereo Computer-Vision Machine-Learning System in Rice Fields.

Site-specific weed management and selective application of herbicides as eco-friendly techniques are still challenging tasks to perform, especially for densely cultivated crops, such as rice. This study is aimed at developing a stereo vision system for distinguishing between rice plants and weeds and further discriminating two types of weeds in a rice field by using artificial neural networks (ANNs) and two metaheuristic algorithms. For this purpose, stereo videos were recorded across the rice field and different channels were extracted and decomposed into the constituent frames. Next, upon pre-processing and segmentation of the frames, green plants were extracted out of the background. For accurate discrimination of the rice and weeds, a total of 302 color, shape, and texture features were identified. Two metaheuristic algorithms, namely particle swarm optimization (PSO) and the bee algorithm (BA), were used to optimize the neural network for selecting the most effective features and classifying different types of weeds, respectively. Comparing the proposed classification method with the K-nearest neighbors (KNN) classifier, it was found that the proposed ANN-BA classifier reached accuracies of 88.74% and 87.96% for right and left channels, respectively, over the test set. Taking into account either the arithmetic or the geometric means as the basis, the accuracies were increased up to 92.02% and 90.7%, respectively, over the test set. On the other hand, the KNN suffered from more cases of misclassification, as compared to the proposed ANN-BA classifier, generating an overall accuracy of 76.62% and 85.59% for the classification of the right and left channel data, respectively, and 85.84% and 84.07% for the arithmetic and geometric mean values, respectively.

Determination of physical and mechanical properties of carrot in order to reduce waste during harvesting and post-harvesting.

Lack of sufficient knowledge about the physical and mechanical properties of agricultural products can result in higher waste of them. Due to the importance of carrot as an agricultural product and lack of much knowledge about how to reduce its waste as well as design and optimize the required harvest and postharvest machinery, this research study was carried out to fill this gap. In this study, physical properties included the length, width, thickness, mean diameter (geometric and arithmetic), mass, volume, density, sphericity, surface area, aspect ratio. The mechanical properties of the samples and their lengths were measured under the conditions of pressure (bruise), bending (break), and shearing of the carrot halves using a Zwick/Roell Instron testing machine based on the recommended standards. The mean geometric mean diameter, surface area, sphericity, volume and true density of the carrot were 49.54 mm, 7758.32 mm2, 0.32%, 70 cm3, and 1.04 g/cm3. In the study of mechanical properties of carrots, the maximum forces required for bruising, bending, and shearing of the carrot fruit were 71.90, 48.60, and 41.14 N, respectively. The results obtained about the physical and mechanical properties can be very useful in reducing carrot waste and mechanizing harvest and postharvest operations by providing us with information that helps us design machinery needed to transfer, sort, separate, wash, package, store, and process carrots.

Detection of sunn pest-damaged wheat samples using visible/near-infrared spectroscopy based on pattern recognition.

The presence of sunn pest-damaged grains in wheat mass reduces the quality of flour and bread produced from it. Therefore, it is essential to assess the quality of the samples in collecting and storage centers of wheat and flour mills. In this research, the capability of visible/near-infrared (Vis/NIR) spectroscopy combined with pattern recognition methods was investigated for discrimination of wheat samples with different percentages of sunn pest-damaged. To this end, various samples belonging to five classes (healthy and 5%, 10%, 15% and 20% unhealthy) were analyzed using Vis/NIR spectroscopy (wavelength range of 350-1000 nm) based on both supervised and unsupervised pattern recognition methods. Principal component analysis (PCA) and hierarchical cluster analysis (HCA) as the unsupervised techniques and soft independent modeling of class analogies (SIMCA) and partial least squares-discriminant analysis (PLS-DA) as supervised methods were used. The results showed that Vis/NIR spectra of healthy samples were correctly clustered using both PCA and HCA. Due to the high overlapping between the four unhealthy classes (5%, 10%, 15% and 20%), it was not possible to discriminate all the unhealthy samples in individual classes. However, when considering only the two main categories of healthy and unhealthy, an acceptable degree of separation between the classes can be obtained after classification with supervised pattern recognition methods of SIMCA and PLS-DA. SIMCA based on PCA modeling correctly classified samples in two classes of healthy and unhealthy with classification accuracy of 100%. Moreover, the power of the wavelengths of 839 nm, 918 nm and 995 nm were more than other wavelengths to discriminate two classes of healthy and unhealthy. It was also concluded that PLS-DA provides excellent classification results of healthy and unhealthy samples (R2 = 0.973 and RMSECV = 0.057). Therefore, Vis/NIR spectroscopy based on pattern recognition techniques can be useful for rapid distinguishing the healthy wheat samples from those damaged by sunn pest in the maintenance and processing centers.