Rice is the staple food for most of the tropical and subtropical countries of the world. This entails large fields of paddy spanning hectares, whose maintenance and care becomes a tedious task for the farmers. The caretakers aren’t able to identify certain types of diseases and aren’t able complete the tedious task of crop care in such a short span. Thus, motivated by this arduous exercise, this project suggests a solution for quick classification of paddy into diseased or healthy plants. If the plant is diseased, the area affected is identified. The image dataset used for this module is obtained from public platforms and consists of 3500 images of healthy and diseased paddy leaves. The classification module is created using deep learning network layers and provides accuracy of up to nearly 70%. This project reviews existing works on image classification using deep learning, introduces a new module for paddy disease classification and gives a refssserence for future work on the subject.
The efforts to increasing the quantity and quality of rice production are obstructed by the paddy disease. This research attempted to identify the major paddy diseases (leaf blast, brown spot and healthy ) using fractal descriptors to analyze the texture of the lesions. The lesion images were extracted manually. The descriptors of `S’ component of each lesion images then used in classification process using probabilistic neural networks.