Paddy Variety Detecting System using Image Recognition

Abstract

The purpose of this research is to develop an advanced automated system for classifying the paddy varieties, based on the image classifying procedure, deep learning techniques, specifically, Convolutional Neural Networks (CNNs), combined with high-resolution images of the eight major rice varieties present in Bangladesh. The motivation can be found in the disadvantages of manual classification techniques, including labor-intensive, error-prone, and cumbersome to apply in rural settings on a large scale. By employing the features at the advanced level of CNNs, this project introduces an AI-based approach to the identification of varieties of rice as: BRRI Dhan 25, BRRI Dhan 28, BRRI Dhan 29, BRRI Dhan 89, BRRI Dhan The methodology required the generation of a dataset, the manipulation of pictures, the application of data augmentation methods and the training of various CNN models such as DenseNet121, VGG16 and MobileNet. The assessment of the performance of the models was performed on the base of accuracy, precision, recall, and F1-score as the criteria, and DenseNet121 turned out prominently among the options. The system has been developed so that it increases the rice variety identification accuracy and time and presents a real alternative solution for farmers, researchers, and policy makers which supports the development of digital agriculture. The next stage for development will be focused on the use of this model within mobile applications to provide real-time support to agricultural practices.