Intellectual Property India Publishes Patent Application for An Optimized Lightweight Deep Learning Framework For Tomato Leaf Disease Detection Using Lenet-5 And Ternary Weights.

MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641105929 A) filed by Dr. Gudapati Syam Prasad; Dr Murari Nancharaiah; Bandi Sri Vara Prasad; Dakarapu Aruna; John Bunyan Vadlapati; Medabalimi Chaitanya; and Dr Padamata Ramesh Babu on September 03, 2026, for An Optimized Lightweight Deep Learning Framework For Tomato Leaf Disease Detection Using Lenet-5 And Ternary Weights..

Inventors include Dr. Gudapati Syam Prasad; Dr Murari Nancharaiah; Bandi Sri Vara Prasad; Dakarapu Aruna; John Bunyan Vadlapati; Medabalimi Chaitanya; and Dr Padamata Ramesh Babu.

The application for the patent was published on September 11, 2026, under issue no. 37/2026.

Abstract: The primary area of this study for crop disease diagnostics now centers on deep learning techniques. However, deep learning techniques require high computational power, which limits their portability. This paper used the potential variant Convolution Neural Network model named LeNet-5 for classification and the Otsu multi- thresholding method with an optimization algorithm for the segmentation of the images. The ternary weight networks are integrated into the LeNet-5 to achieve better balance between model compression rate and accuracy with potentially low computational requirements model. The classifier is trained using the Plant Village dataset which contains images of tomato leaves with various types of diseases. This can be calculated using different performance metrics like precision, recall, F1-score, and accuracy. These are compared with three existing approaches Xception, ResNet50, and VGG16. From this comparison the proposed approach gives the best accuracy for classification.

Disclaimer: Curated by HT Syndication.