MUMBAI, India, Aug. 31 -- Intellectual Property India has published a patent application (202641100117 A) filed by Karpagam College Of Engineering; Karpagam Academy Of Higher Education; Dr A Rajendran; and Anujeyanthi M on August 19, 2026, for Banana Leaf Disease Detection Using Deep Learning Techniques.
Inventors include Dr A Rajendran; and Anujeyanthi M.
The application for the patent was published on August 28, 2026, under issue no. 35/2026.
Abstract: The present invention relates to a system for detecting and classifying banana leaf diseases using deep learning techniques. Banana crops are highly vulnerable to fungal, bacterial, and viral infections that significantly reduce yield and crop quality. Conventional manual inspection methods are time-consuming and prone to human error, especially under varying environmental conditions. The proposed system processes high-resolution images of banana leaves using image preprocessing techniques including resizing, normalization, noise reduction, and segmentation to isolate the region of interest. A Convolutional Neural Network (CNN) architecture with transfer learning is employed for multi-class disease classification. The system identifies multiple disease types and supports severity-level assessment to enable timely agricultural intervention. Performance evaluation is conducted using standard metrics such as precision, recall, F1-score, and confusion matrix analysis. Experimental results demonstrate a classification accuracy of 95.23%, indicating high reliability and strong predictive capability of the developed model. The system is scalable and can be integrated with mobile devices, IoT-based monitoring platforms, or field-deployable agricultural systems.This invention provides an efficient and intelligent framework for banana leaf disease detection, supporting precision agriculture and sustainable crop management.
Disclaimer: Curated by HT Syndication.
