Globally, rice consumption is widespread and the market for it is constantly in high demand. The rice production industry thrives because of market demand, which is primarily driven by rice quality. Unfortunately, malnutrition affects over three billion people worldwide. To combat this issue, increasing the mineral concentration in crops is a sustainable and cost-effective approach. In the context of rice quality analysis, these traits could encompass parameters such as size, shape, colour, and texture. This research work contributes to the quality of rice to protect consumers from buying low-quality rice. This case study proposes a system using deep learning techniques such as convolutional neural networks (CNN) and bi-long short-term memory (Bi-LSTM) models to enhance our understanding of rice quality attributes, as well as it helps in predicting the rice grain to be accurate in less time when compared to existing system (Convolutional Neural Network).