Hybrid Enhanced Featured AlexNet for Milled Rice Grain Identification

Rice is a widely cultivated grain with numerous genetic variants that can be distinguished by their unique texture, shape, and color characteristics. Accurate classification and evaluation of seed quality depend on the ability to identify these traits. In this study, we propose a novel Hybrid Enhanced Featured AlexNet model for identifying eight varieties of milled rice, including arborio, basmati, ipsala, jasmine, jhili, masoori, HMT, and karacadag. Our approach combines the use of a pre-trained AlexNet model with multilayer feature fusion to extract deep features, which are then supplied to a Support Vector Machine (SVM) for classification. Our proposed model achieves an impressive accuracy of 99.63%, sensitivity of 99.63%, specificity of 99.95%, precision of 99.64%, and an F1 score of 99.63%. Our methodology has significant potential for application in the food processing sector to determine the price of various milled rice varieties.