Intellectual Property India Publishes Patent Application for 'System And Method For Explainable Plant Disease Detection Using Resnet Convolutional Neural Networks' Filed by Malla Reddy Engineering College For Women; and Malla Reddy University

MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202641018319 A) filed by Malla Reddy Engineering College For Women; and Malla Reddy University, Hyderabad, Telangana, on Feb. 18, for 'system and method for explainable plant disease detection using resnet convolutional neural networks.'

Inventor(s) include Y. Madhaveelatha; Ch Sandeep Reddy; Kalyana Chakravarthi Agnihothram; Kurada Phaneendra; Ramesh Challa; Nenavath Chander; R. Kiran Kumar; and G. Ravi.

The application for the patent was published on Feb. 27, under issue no. 09/2026.

According to the abstract released by the Intellectual Property India: "Agriculture is a critical sector for global food security, yet plant diseases continue to reduce crop yield and quality worldwide. Traditional methods of disease identification rely on manual inspection by experts, which is slow, subjective, and error-prone. The present invention introduces a Plant Disease Detection System based on Residual Convolutional Neural Networks (ResNet-CNN). The system preprocesses leaf images through resizing, normalization, and noise removal, thereby ensuring consistency across diverse datasets. Deep hierarchical features are extracted using residual blocks, convolutional layers, and pooling layers, followed by dense layers for classification. The invention achieves high accuracy, with experimental results demonstrating performance exceeding 98 percent across multiple plant diseases. The system further incorporates explainability by generating accuracy and loss graphs during training, enabling transparency in model behavior. A graphical interface allows farmers to upload test leaf images and receive instant disease predictions with confidence scores. Deployment into mobile and IoT platforms ensures accessibility in rural environments, supporting precision agriculture and targeted pesticide usage. This invention provides a scalable, automated, and explainable solution for plant disease detection, bridging the gap between traditional inspection and modern agro-tech innovation."

Disclaimer: Curated by HT Syndication.