Published Paper Details:

Rice is one of the most widely cultivated food crops in the world. However, there is a significant probability that high amounts of salt, especially at the seedling stage, would have a detrimental effect on rice growth. To prevent a decrease in rice productivity, it is crucial to quickly discover and develop salinity-tolerant rice crop types, particularly at the seedling stage. Expertise from humans is required for the classification of visual signals and the conventional way of a standard assessment system for identifying rice crop salt stress. It's not only time-consuming, but it often leads to mistakes that lead to inaccurate classification. The research shows the need for a deep learning developed model over the conventional approach of measuring rice crop sensitivity to salt stress during the seedling stage to detect and classify salinity stress in rice seedlings using field images. Therefore, we employ pre-trained deep learning approaches, such as VGG 16, VGG 19 to develop the classification model. These techniques are developed in Jupyter Notebook using Python programming. The model can classify images of rice seedlings into scores of 1, 3, 5, 7, and 9, demonstrating the critical need for a computer-based classification system for salinity prediction that could be used as a tool for automating the classification process for rice development to aid researchers and farmers in the rice crop management system.