MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202611027454 A) filed by Manipal University, Jaipur, Rajasthan, on March 9, for 'a system and method for automated rice disease detection using hybrid cnn-xception deep learning architecture.'
Inventor(s) include Manashjyoti Baishya; Dr Saikat Samanta; and Dr Achyuth Sarkar.
The application for the patent was published on May 1, under issue no. 18/2026.
According to the abstract released by the Intellectual Property India: "The present invention relates to a system and method for automated rice disease detection using hybrid CNN-Xception deep learning architecture. The system comprises: a data collection module to collect rice leaf image from field and dataset sources; a data preprocessing module configured to normalize and resized the image; a feature extraction module combines the high-level feature extraction capabilities of the Xception model with the local texture learning capabilities of CNN to recognize diseases in the rice leaves from their image; and a display unit to display the results. The hybrid architecture improves classification performance, convergence speed, and generalization ability by extracting both local texture features and high-level abstract features. Experimental results demonstrate that the proposed hybrid model achieves an accuracy of 97.85%, surpassing conventional deep learning architectures. The innovation offers a scalable, automated, and efficient solution for crop monitoring and real-time smart agriculture systems."
Disclaimer: Curated by HT Syndication.
