Published Paper Details:

Rice is a cereal grain that is dominantly consumed by more than half of worlds population and is very significant in Indian agricultural economy. Rice is number one, most eat in food globally followed closely by other staples like wheat(in bread ) and maize(corn). Agriculture and allied sectors contribute about 16 to 18% of India's GDP, despite its lower GDP share, the sector employees over more than 40% of the total population. And hence, India is among leading producers and exporters of rice. However, the crop yield as significantly threatened by diseases such as bacterial Blight, brown spots, leaf blasts etc, which can cause potential yield and quality loss if not identified properly. Farmers majorly rely on manual field assessment, which is labour intensive ,time consuming and often could lead to Miss identification and significant economic loss. Recent advancement in fields like machine, learning, deep learning, and hyperspectral imaging has automated data driven approaches that are capable of improving detection, accuracy and efficiency. This study critically examine is more than 10 research works published between 2019 - 2025 covering traditional tools, techniques, frameworks, and algorithms for object detection and imaging techniques. And after a thorough systematic research and evaluation, a detection system was developed to identify rise, disease and help reduce yield loss. After comparatively evaluating the researches, it has indicated that deep learning models consistently demonstrate a superior performance frequently achieving a higher accuracy level more than 95% while hyperspectral and UAV base system offer potential for early stage disease identification despite practical cost constraints. This review identifies existing research gaps and focuses on need for scalable, lightweight and farmer friendly disease detection system to support sustainable farming in India and contribute to global agricultural application.