Intellectual Property India Publishes Patent Application for Deep Learning Based Plant Disease Detection

MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641107613 A) filed by Mr. M. Mohammed Kasim; Dr. Yaswanth Kumar Avulapati; Dr C. Srisailam; K. Shalini; Mr. Jai Kumar M; Ms. Mohanapriya R; Mr. Mounish Chakkravarthi M; and Ms. Prethikaa G R on September 06, 2026, for Deep Learning Based Plant Disease Detection.

Inventors include Mr. M. Mohammed Kasim; Dr. Yaswanth Kumar Avulapati; Dr C. Srisailam; K. Shalini; Mr. Jai Kumar M; Ms. Mohanapriya R; Mr. Mounish Chakkravarthi M; and Ms. Prethikaa G R.

The application for the patent was published on September 11, 2026, under issue no. 37/2026.

Abstract: The present invention relates to a Deep Learning Based Plant Disease Detection System for automatic identification and classification of plant diseases using digital images of plant leaves, stems, fruits, or other visible plant parts. The system comprises an image acquisition module, image preprocessing module, deep learning-based feature extraction and classification module, disease severity estimation module, and an output and recommendation module. Images captured using a mobile device, digital camera, drone, or other imaging device are processed to remove noise, normalize illumination, resize the image, and enhance disease-related characteristics. A trained convolutional neural network (CNN), transfer-learning model, or hybrid deep learning architecture extracts discriminative features such as color variations, spots, lesions, texture patterns, fungal growth, chlorosis, necrosis, and structural abnormalities. The extracted features are classified into healthy and one or more disease categories. The system may further estimate disease severity based on the affected area and generate an early warning and suitable crop-management recommendation. The proposed invention enables rapid, non-invasive, automated, and scalable plant disease detection with reduced dependency on manual inspection and expert availability. The system can be deployed on cloud, edge, mobile, or IoT-enabled agricultural platforms for real-time precision agriculture applications.

Disclaimer: Curated by HT Syndication.