مجید دولتی

Persian cumin plays a significant role in both exports and domestic industries of Iran. Today, due to the widespread availability of counterfeit cumin in the market, identifying authentic Persian cumin from its counterfeit counterparts has become increasingly essential. Among the various criteria for identification, color and texture indices are particularly notable. Traditional methods, such as manual and visual inspections, are not only time-consuming but also prone to a high degree of human error. In this study, in order to propose a new, precise, and rapid method, machine vision technology was utilized to extract the color and texture features of cumin from its images. Subsequently, a multi-layer perceptron artificial neural network with a backpropagation algorithm and a hidden layer was employed, evaluating different neurons in this layer to perform the process of distinguishing authentic Persian cumin from counterfeit varieties in the market. In this study, five samples of authentic Persian cumin and four samples of counterfeit cumin, were evaluated. The results showed that the highest average classification and identification accuracy of authentic cumin from counterfeit cumin, using a neural network with one hidden layer and employing a sigmoid transfer function in this layer and a linear function in the output layer with the Levenberg-Marquardt learning algorithm, were 93.51% for color features, 95.86% for texture features, and 95.59% for the combination of these two features (color-texture). However, the findings showed that machine vision technology and artificial neural networks have a high capability in accurately identifying authentic Persian cumin from counterfeit samples.

The present study was carried out in order to compare the effect of four types of conventional pistachio drying systems including diesel- and gas-fueled wagon and carriage dryers on the pistachio shell opening rate, shell damage, drying uniformity, storage shelf-life, pistachio quality, fuel consumption, energy efficiency, and economic efficiency. Two well-known pistachios types including elongated and round types were chosen for this study. The obtained results showed that: A) The rate of pistachios shell opening using a diesel-fueled wagon dryer was profoundly higher than those of the other systems due to its high drying air temperature (90 oc) and the thin layer of the moist product (20 cm) within the dryer. B) The wagon dryers led to less damage (around 39 percent) to pistachio nuts because of the absence of agitation. C) Generally, the energy consumption of wagon drying systems was lower compared with the carriage systems (around 50 percent). D) Higher drying uniformity was obtained using the gas-fueled carriage dryer due to an appropriate agitation. E) Dryer type and storage time up to 6 months, had no significant effect on the oil percentage, peroxide number, and pistachios quality. F) The gas-fueled wagon dryer had the highest economic profitability among the systems studied. G) The gas-fueled wagon dryer had the highest energy efficiency compared (around 15 percent) with the other systems. H) The pistachio types did not have a significant effect on the investigated parameters.

Nowadays, citrus fruits, especially oranges, is very important in the human nutrition regime, and its quality characteristics assessment is very important. This study aimed to predict some biochemical characteristics of blood orange, using machine vision and artificial neural networks. In this experiment, the amount of vitamin C content, sugar content, and acidity (pH) were obtained using destructive laboratory methods. Images of blood orange samples were captured and 108 texture features and 57 color features were extracted on CIElab, RGB, HSV, and HIS color spaces and finally, the artificial neural networks method has been used to estimate the desired properties. To evaluate and select the most optimal artificial neural network, a feed-forward neural networks with Levenberg-Marquardt learning algorithm, the different number of neurons, and different transfer functions in the hidden and output layers was used. Finally, using the best neural network and 165 textural-color features, the amount of vitamin C content, sugar content, and pH were estimated with a correlation coefficient of 0.950, 0.968, and 0.884, respectively. Therefore, considering the appropriate correlation coefficient, machine vision and image processing technology can estimate some biochemical characteristics of blood oranges accurately.

Camel meat can be a suitable alternative for other red meat types in human nutrition, due to its low cholesterol and low-fat content and the appropriate protein content. This research aims to investigate and evaluate the fat content and freshness of camel meat using machine vision technology as a non-destructive method. Therefore, using image processing as a non-destructive method and Soxhlet device as a destructive method, the amount of fat content was predicted, and also the freshness was classified for camel meat. In the image processing section, 108 textual features and 39 color features were extracted in the RGB, HSV, HIS, and CIElab color spaces. Moreover, to predict the freshness and quality of meat, feed-forward back propagation artificial neural networks with one and two hidden layers, a various number of neurons, and threshold functions were used. Also, according to the regression diagram of fat content obtained from the destructive method (fat content obtained from Soxhlet device) with fat content obtained from non-destructive method (machine vision), the coefficient of determination and accuracy between them achieved 0.841. The results of the evaluation of the neural networks showed that the best desirable network for classification based on freshness is a one-hidden layer network with topology 147-3-1, tangent-sigmoid transfer function at hidden layer and purelin transfer function at output layer (R2= 0.996), and also to prete of fat content the best network is two-hidden layer network with linear, log-sigmoid, log-sigmoid transfer function at first hidden layer, second hidden layer and output layer respectively (R2= 0.99). Therefore, the results of this study show that the proposed system with the help of machine vision technology can predict the freshness and fat content of camel meat with acceptable accuracy.

Spices are the most valuable medicinal plants used in food and medical science industries and due to quality and price diversity between various species, distinction, classification and separation of them based on purity and quality degree have great importance. Spices are produced in different countries, including India, Pakistan, China, and East and South Asian countries. The difference in the percentage of aromatic compounds in various types of spices from different regions has led to a distinction between spices. Also, profitable individuals for economic purposes and more profit without regard to the general health of the community will lead to the creation of adulteration in different types of spices. The most important of these adulterations is the addition of volatile ingredients such as cubeb pepper and palm kernel powder in black pepper.

In this study, an olfactory machine system based on eight metal oxide semiconductor sensors in combination with pattern recognition methods were used to classify and separate of black pepper samples based on geographic origin and also to detect cubeb pepper adulteration and palm kernel powder. The adulterated black pepper samples were tested with different adulteration levels (10, 20 and 30%).The fractional method was used to improve and optimize the electronic nose output signals before entering diagnostic methods. In order to analyze the extracted data from the sensor response signal, the principal component analysis method (PCA) was used. Based on the results, PCA with two main components of 96% for black pepper and 95% of cubeb pepper and palm kernel adulteration can be described from the variance of data. Also, three methods of linear separation analysis (LDA), Support vector machine (SVM) and decision tree (DT) were used to classify the samples. The use of the LDA method for black pepper showed a classification precision of 100%, and for adulterations, accuracy was 97.14%.

The results showed that SVM with Gaussian function has the highest accuracy in classifying black pepper samples, cubeb pepper, and palm kernel adulteration Also, the success rate of the DT method in separating and categorizing black pepper, cubeb pepper, and palm kernel was 96.66% and 88.5%  respectively.According to the results obtained, the machine olfaction system in combination with pattern recognition methods has the ability to detect and classify different black pepper samples from different geographical origin and the lowest level of adulteration.

Non-chemical treatments are an approach for improving seed germination. In order to evaluate the effects of the magnetic field application on onion seed germination and seedling growth indices, a quadrupole magnetic field system was designed and fabricated. It was also compared with a dipole magnetic field system. In the quadrupole system, each coil consisted of three layers and the cores were moved inside the coils. These arrangements make it possible to change the magnetic field intensity in addition to input current setting. The experiments were conducted based on factors including the type of system (bipolar and quadrupole), magnetic flux density (75, 150, 300 and 600 μT) and duration of the field application (15, 30, 60 and 120 min). Germination percentage, germination rate, mean germination time, seedling vigor index, shoot length, root length, fresh weight of shoot and root, fresh weight of seedling, dry weight of shoot and root were measured. The results showed significant effects on seed germination and seedling growth of onion. In most germination characteristics, the quadrupole system had a better impact than the bipolar system. For many traits (except for weights), the increase in field intensity degraded the traits. Quadrupole system that applied the magnetic field of 600 μT for 15 minutes, yielded 63% increase in the total seedling weight. Most of the germination traits were not affected by exposure time. Further investigations are required for shorter exposure times compared to used durations in this study.

In present study, image processing technology and ANNs were used to identify the pistachio leaf pests include Ocneria terebinthina stgr and agonoscena pistaciae. The color images were captured from leaves of Ohadi pistachio variety and, color, texture, morphological and texture-color features were extracted from images in order to detection and classification of pests. To achieve the best models of ANNs, different types of ANNs and extracted features were evaluated and the following choices were selected according to the performance of different developed ANNs as the bests; A:The two-layer back propagation ANNs with two hidden layers with SigmoidAxon transfer function and TanhAxon as transfer function in output layer, by using the six color features (variance, mean, standard deviation, skewness, kurtosis and smoothness) with an accuracy of 93.3%, B: The two-layer back propagation ANNs with two hidden layers with SigmoidAxon transfer function and Linear transfer function in output layer, by using the five texture features (entropy, contrast, correlation, energy, homogeneity) with an accuracy of 95%, C: The two-layer back propagation ANNs with two hidden layers, with TanhAxon transfer function and Linear transfer function in output layer, by using the five morphological features (Area, perimeter, convex hull area, extent and solidity) and also, 11 texture-color features with accuracy of 86.7% and 98.3% respectively. The results showed the image processing technology and ANNs, had excellent ability to identify and classification of pistachio leaf pests.