Search

The presence of weed seeds and other impurities in the wheat grains affect the identification quality of the wheat grains. This study explores the possibility of identifying the wheat in the wheat grain mass and estimates the amount of impurities in the wheat mass based on the video processing combined with the artificial neural network (ANN) integrated by particle swarm optimization (PSO) algorithm. After pre‐processing the video of the mass movement on the conveyor belt, 35 shapes, color, and textural features were extracted from each grain sample in the image in the presence of the MATLAB software and image processing (IP) toolbox. The data obtained from the IP section were categorized into two approaches. The first one, purposes the identification of the wheat grains in the grain mass, and the other one, identifies each components in the wheat mass. Both of them employs the hybrid ANN‐PSO algorithm to achieve the highest classification accuracy and the lowest error value. According to the results, ANN with the architecture of 36‐10‐10‐5 and ANN with the architecture of 36‐8‐8‐5 overtakes the other architectures with the highest accuracy and performance values for training (100 and 100%) and testing phases (100 and 86.66%), respectively for the first and second approaches. Accordingly, based on the results of the hybrid ANN‐PSO algorithm, the highest classification accuracy was 98.62% and 97.77% (for training and testing phases, respectively) and 76.08% and 73.1% (for training and testing phases, respectively) related to the first and the second approaches, respectively. Finally, the video processing using ANN can be considered as a powerful approach for identifying the impurities in the wheat grain mass. Practical applications: One of the major problems in wheat and similar mass products is the presence of impurities inside the total mass, which drastically reduces the quality and the marketability of the product. Conventional methods of detecting the amount of impurities in the grain mass are always accompanied by difficulties such as lack of precision, time consuming, and tedious. The use of new technologies such as machine vision and artificial intelligence have been considered as the important tools in this regard. One of the practical applications of this study is to detect the amount of impurities in wheat grain mass at the inlet of silos and in pricing on grain masses. The system proposed in this study can accurately detect and report impurities in wheat grain mass. [ABSTRACT FROM AUTHOR]

Considering the fact that the presence of bug-damaged wheat in the bulk results in a decrease of the flour quality and its final product, which is bread, it is necessary to differentiate the bug-damaged wheat grains from the healthy ones. Therefore, the present study investigated the mechanical properties of bug-damaged and healthy wheat grains of the Azar cultivar. By making use of these mechanical properties, it would be possible to provide a more precise texture identification of the bug-damaged wheat grains compared to the healthy ones. In this study, the mechanical properties (rupture energy, toughness and apparent elastic coefficient) were determined under compressive loading, with four levels of loading velocity (5, 15, 25 and 35 mm.min-1) and four levels of moisture content (9, 11.5, 14 and 16.5% wet basis) in both bug-damaged and healthy wheat grains. Due to the significant difference in the mean value of apparent elastic coefficient between the bug-damaged grains (74.779 MPa) and the healthy ones (289.071 MPa), this parameter can be employed as the most appropriate factor to distinguish the bug-damaged wheat grains from the healthy ones. [ABSTRACT FROM AUTHOR]

Wheat is one of the most important strategic crops in Iran and in the world. The major component that distinguishes wheat from other grains is the gluten section. In Iran, sunn pest is one of the most important factors influencing the characteristics of wheat gluten and in removing it from a balanced state. The existence of bug-damaged grains in wheat will reduce the quality and price of the product. In addition, damaged grains reduce the enrichment of wheat and the quality of bread products. In this study, after preprocessing and segmentation of images, 25 features including 9 colour features, 10 morphological features, and 6 textual statistical features were extracted so as to classify healthy and bug-damaged wheat grains of Azar cultivar of four levels of moisture content (9, 11.5, 14 and 16.5% w.b.) and two lighting colours (yellow light, the composition of yellow and white lights). Using feature selection methods in the WEKA software and the CfsSubsetEval evaluator, 11 features were chosen as inputs of artificial neural network, decision tree and discriment analysis classifiers. The results showed that the decision tree with the J.48 algorithm had the highest classification accuracy of 90.20%. This was followed by artificial neural network classifier with the topology of 11-19-2 and discrimient analysis classifier at 87.46 and 81.81%, respectively. [ABSTRACT FROM AUTHOR]

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 (R 2  = 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. [ABSTRACT FROM AUTHOR]