Abstract - Worldwide security of food hinges on two essential staple crops paddy and wheat. However, their yield is sometimes threatened by a number of diseases, such as Russet leaves, Explosion and bacterial blight, which can cause significant production losses. The goal of this project is to develop a precise and effective technique for identifying agricultural diseases in wheat and paddy using state-of-the-art image processing and machine learning approaches. The technique analyzes high-resolution images of crop leaves and applies deep learning models to precisely identify and classify disease symptoms. The proposed approach offers a rapid, scalable, and cost-effective early disease detection option, enabling farmers to conduct targeted and timely corrective action. This project's goals are to boost Production from farming and minimize monetary losses, and promote sustainable farming techniques.

Keywords: Crop disease detection, rust on leaves, microbial blight, blast disease, precision farming, plant health monitoring, artificial intelligence in agriculture, and plagues of wheat and rice, deep learning, machine learning, image detection and prompt identification of infection.

| DOI: 10.17148/IARJSET.2025.12212