Classification of Rice Varieties Using VGG-19 and Alexnet

A comparative analysis of deep learning techniques for the classification of rice varieties. Leveraging Convolutional Neural Networks (CNNs), VGG19, and AlexNet architectures, we evaluate their performance on a dataset of high-resolution rice grain images. The study showcases the effectiveness of these models in accurately categorizing diverse rice varieties. Results indicate that while all models exhibit high classification accuracy, VGG19 demonstrates superior performance at the cost of increased computational resources. AlexNet, with its simpler architecture, provides competitive results with reduced computational demands. Traditional CNN architecture also performs admirably in this context. A dataset of 25 varieties of rice has been implemented. By using these algorithms the rice type can be classified and It also provides additional information of the rice and their health benefits.