MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202621100247 A) filed by Deepali Rajaram Naglot; Deepa S Deshpande; and Archana H Telgaonkar on August 19, 2026, for System For Devnagari Sign Language Alphabet Recognition.
Inventors include Deepali Rajaram Naglot; Deepa S Deshpande; and Archana H Telgaonkar.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: The absence of reliable and standardized technological solutions for Devnagari Sign Language (DSL) continues to hinder seamless communication for individuals with speech and hearing impairments in regions where Devnagari-based languages are widely used. Existing systems depend heavily on raw images, are highly sensitive to environmental changes, and fail to provide consistent performance across diverse users, backgrounds, and lighting conditions. This invention presents a novel DSL alphabet recognition system that overcomes these limitations by generating a diverse gesture dataset, extracting precise hand landmarks, and employing a hybrid spatial–temporal learning model to recognize 47 Devnagari alphabet gestures in real time. By combining robust landmark representation with an integrated Conv-based spatial feature extractor and temporal sequence learner, the system delivers stable and highly reliable gesture recognition across varied real-world conditions. The proposed system provides a robust, scalable, and efficient framework for gesture-based communication, enabling practical deployment in real-world assistive and educational applications.
Disclaimer: Curated by HT Syndication.
