MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641106628 A) filed by Nitte Meenakshi Institute Of Technology, Nitte Deemed To Be University, Bengaluru; Mrs. Sushma K; Mrs. Shalini Joseph; Dr. Sudhakar K; Dr. Rubini P; and Parameshachari Bidare Divakarachari on September 04, 2026, for Automated Plant Disease Diagnosis Via Cnn And Yolo-Based Region Extraction.
Inventors include Nitte Meenakshi Institute Of Technology, Nitte Deemed To Be University; Mrs. Sushma K; Mrs. Shalini Joseph; Dr. Sudhakar K; Dr. Rubini P; and Parameshachari Bidare Divakarachari.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: ABSTRACT OF THE INVENTION Title: Automated Plant Disease Diagnosis via CNN and YOLO-Based Region Extraction The present invention provides a system and method for automated plant disease diagnosis that integrates YOLO-based region of interest extraction with a custom 10-layer convolutional neural network classifier. The YOLO module automatically detects and isolates leaf areas from uploaded images, eliminating background noise including soil, weeds, and other vegetation. The cropped leaf region is processed through the CNN model comprising convolutional, pooling, and fully connected layers with softmax classification for multi-class disease categorisation. Trained on 4,500 images with extensive data augmentation over 60 epochs, the system achieves 96% validation accuracy and 94% test accuracy. A treatment recommendation engine maps diagnosis results to actionable treatment protocols delivered through mobile and web interfaces, enabling farmers to receive instant, accurate plant disease diagnosis and treatment guidance.
Disclaimer: Curated by HT Syndication.
