MUMBAI, India, Feb. 13 -- Intellectual Property India has published a patent application (202641008121 A) filed by Dr. Jayasri B S; Dr. Lokesh S; Dr. Vidya Raj C; Ms. Bhuvana S; Mr. Shivaprasad Devadiga; Mr. Prajwal Gr; and Mr. Prajwal Narayana Patgar, Mysuru, Karnataka, on Jan. 28, for 'early detection of paddy disease and severity based classification using variants of cnn-a step towards smart agriculture.'
Inventor(s) include Dr. Jayasri B S; Dr. Lokesh S; Dr. Vidya Raj C; Ms. Bhuvana S; Mr. Shivaprasad Devadiga; Mr. Prajwal Gr; and Mr. Prajwal Narayana Patgar.
The application for the patent was published on Feb. 13, under issue no. 07/2026.
According to the abstract released by the Intellectual Property India: "The present invention discloses a computer-implemented system and method for early detection and severity-based classification of paddy leaf diseases using deep learning. The system employs a multi-task convolutional neural network to simultaneously identify paddy diseases and estimate their severity on an ordinal scale ranging from one to nine. Input images of paddy leaves are preprocessed and analyzed using a shared feature extraction network, followed by dual output heads for disease classification and severity regression. Based on the predicted severity score, the system categorizes diseases into curable and non-curable stages and provides actionable decision support to farmers. The invention reduces dependency on manual inspection, prevents excessive pesticide usage, improves crop management efficiency, and supports sustainable agricultural practices. The system is region-specific, scalable, and suitable for real-time deployment, making it a practical solution for smart agriculture and precision farming applications."
Disclaimer: Curated by HT Syndication.
