Intellectual Property India Publishes Patent Application for 'Hyper Neural Network Driven Methodology For Efficient Wheat Crop Disease Detection' Filed by B. Nithyasundari; R. S. Vijayashanthi; L. Chithra; and S. A. Engineering College

MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541112332 A) filed by B. Nithyasundari; R. S. Vijayashanthi; L. Chithra; and S. A. Engineering College, Chennai, Tamil Nadu, on Nov. 17, 2025, for 'hyper neural network driven methodology for efficient wheat crop disease detection.'

Inventor(s) include B. Nithyasundari; R. S. Vijayashanthi; and L. Chithra.

The application for the patent was published on Jan. 9, under issue no. 02/2026.

According to the abstract released by the Intellectual Property India: "Many new ways of solving certain serious problems have emerged in the agricultural sector as a result of the fast growth of technology. This research automates the identification of several wheat leaf diseases with amazing efficiency using the Python programming language and architecture based on neural networks. The present invention relates to a system and method for automated identification and classification of diseases in wheat crops using a Hyper Neural Network Learning (HNNL)framework. The proposed approach integrates a hypernetwork-based adaptive learning mechanism with pre-trained convolutional neural network (CNN) models to extract and optimize discriminative image features. The HNNL model dynamically generates parameter weights for the CNN classifier, enabling efficient differentiation between healthy and disease-affected wheat plants under varying imaging conditions.In an experimental evaluation comprising a dataset of 1,500 images including one class representing healthy crops and eleven classes representing distinct disease conditions, the proposed system achieved a reliability rate of 96.46%. Data augmentation through multi-angle image rotation was employed to improve model generalization and feature robustness. The combination of hypernetwork-based learning and conventional CNN architectures demonstrated enhanced diagnostic precision in detecting wheat crop diseases, thereby offering an efficient and scalable solution for Agricultural disease monitoring and management."

Disclaimer: Curated by HT Syndication.