Intellectual Property India Publishes Patent Application for 'High-Fidelity Via Metaheuristic Optimization And Convolutional Block Attention-Powered Residual Neural Architecture Pepper Leaf Disease Recognition System' Filed by Pranveer Singh Institute Of Technology

MUMBAI, India, Feb. 6 -- Intellectual Property India has published a patent application (202511132499 A) filed by Pranveer Singh Institute Of Technology, Kanpur, Uttar Pradesh, on Dec. 27, 2025, for 'high-fidelity via metaheuristic optimization and convolutional block attention-powered residual neural architecture pepper leaf disease recognition system.'

Inventor(s) include Dr. Piyush Bhushan Singh; Vaishnavi Srivastava; Utsav Verma; Mr. Ashish Tripathi; Dr. Vatsya Tiwari; Dr. Esha Tripathi; Dr. Sumit Chandra; Dr. Prashant Kumar Mishra; Dr. Rahul Deo Shukla; and Dr. Abhay Kumar Tripathi.

The application for the patent was published on Feb. 6, under issue no. 06/2026.

According to the abstract released by the Intellectual Property India: "This work utilizes a novel hybrid deep learning model for pepper leaf disease detection based on an attention mechanism and metaheuristic optimization. The system uses a Grey Wolf Optimizer (GWO) to optimize Contrast Limited Adaptive Histogram Equalization (CLAHE) parameters for better image enhancement and to enhance the Contrast of the image by enhancing the visibility of lesions and suppressing the noise. To selectively focus on "what and where" to attend in both channel and spatial dimensions, we propose a Convolutional Block Attention Module (CBAM) which is integrated into a typical Residual Neural Network-50 (ResNet50) and effectively attends to disease-responsible patterns while suppressing the background clutter. The solution is ideal for real-time, scalable use on low-power devices enabling early-stage disease detection and scalable agricultural monitoring."

Disclaimer: Curated by HT Syndication.