Identification of impurity in wheat mass based on video processing using artificial neural network and PSO algorithm

Abstract

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.