Automated Cashew Kernel Grading Using Machine Vision

Quality of food and agricultural products is vital for farmers and consumers. Quality based classification of these products is being carried out manually in the industry which is tedious and expensive. Computer Vision systems can be used to automate the classification process. Automation can reduce the production cost and improve the overall quality. A computer vision system captures the image of the underlying object and transmits it to an image processor. The processor, after processing the image, presents it to a pattern recognizer. The recognizer performs the quality assessments and classifies the underlying object into pre-specified quality classes. Previous studies in this regard used minimal features to perform classification which reduces the accuracy. In the proposed approach more features are used which significantly improves the automation process. Automation process faces several challenges like identifying appropriate features and the best classifier. This study tries to grade cashew nuts based on external features like color, texture, shape and size. The effect of various pre-processing operations on the grading process is also studied. Five different classifiers were used and their performance in terms of accuracy is observed. Among the classifiers, Back Propagation Neural Network proved to be the most optimal.