MUMBAI, India, July 13 -- Intellectual Property India has published a patent application (202621069902 A) filed by Symbiosis International Deemed University on June 03, 2026, for A Real-Time Sign Language Gesture Recognition And Translation System With Integrated Text-To-Speech Output.
Inventors include Dr. Snehlata Wankhade; Parth Daware; Jayesh Mundle; and Aditya Yadav.
The application for the patent was published on July 10, 2026, under issue no. 28/2026.
Abstract: ABSTRACT A REAL-TIME SIGN LANGUAGE GESTURE RECOGNITION AND TRANSLATION SYSTEM WITH INTEGRATED TEXT-TO-SPEECH OUTPUT The present invention discloses real-time sign language gesture recognition and translation system (100) that enables communication between sign language users and non-sign language users. The system (100) comprises an image acquisition module (110) for capturing video frames from a camera, a hand landmark detection module (120) for extracting twenty-one three-dimensional hand landmark coordinates using a pre-trained hand detection framework, a landmark normalization module (130) for normalizing the extracted coordinates with the wrist as origin and unit scale, a multilayer perceptron classifier module (140) for classifying normalized landmark feature vectors into corresponding gesture labels, a sentence formation module (150) for accumulating predicted letters into words and sentences, and a text-to-speech conversion module (160) for converting accumulated text into audible speech. The system (100) operates entirely on a general-purpose computing device (180) with a standard webcam, without requiring specialized hardware, achieving real-time performance with approximately ninety-nine percent classification accuracy under controlled conditions. [
Disclaimer: Curated by HT Syndication.
