MUMBAI, India, Aug. 12 -- Intellectual Property India has published a patent application (202641094265 A) filed by Mohan Babu University on August 04, 2026, for Cotton Leaf Disease Identification Using Deep Learning.

Inventors include Dr. P. Baby Maruthi; and Mr. Vutukuru Sujith.

The application for the patent was published on August 07, 2026, under issue no. 32/2026.

Abstract: The growing challenges in modern agriculture, especially in cotton production, have emphasized the urgent need for intelligent systems that can ensure early detection and effective management of crop diseases. Traditional methods of disease identification, which rely heavily on manual observation by experts, are often time- consuming, inconsistent, and ineffective at scale. In response, recent advancements in artificial intelligence and deep learning have opened new pathways for revolutionizing disease diagnosis in agricultural domains. This study focuses on the development and deployment of an automated system for cotton leaf disease identification using deep learning techniques. Specifically, the project integrates convolutional neural networks (CNNs) to process and classify leaf images into multiple categories such as bacterial blight, cotton leaf curl virus, fusarium wilt, and healthy. These models are trained on large datasets collected under diverse environmental conditions, significantly improving the accuracy of detection and enabling robust generalization across unseen samples. By leveraging image inputs from mobile devices, drones, or field sensors, the proposed system ensures real-time, scalable, and cost-effective disease identification. The approach aids farmers and agronomists in making proactive crop management decisions, reducing dependency on manual inspection and minimizing yield losses. This solution finds applications in smart farming, precision agriculture, and rural agricultural support systems, contributing to improved crop health monitoring, food security, and sustainable agricultural practices.

Disclaimer: Curated by HT Syndication.