MUMBAI, India, Aug. 17 -- Intellectual Property India has published a patent application (202641072354 A) filed by Srm Trp Engineering College on June 11, 2026, for An Ai-Based System That Converts Sign Language Gestures From Video Into Text Or Speech Using Deep Learning.
Inventors include S. Rajesh; Sathish. S; and Sivanesvaran N.
The application for the patent was published on August 14, 2026, under issue no. 33/2026.
Abstract: This invention presents an AI-based system for recognizing sign language gestures from video input and converting them into text or speech. The system captures real- time video using a standard camera and processes it through preprocessing techniques such as frame extraction, resizing, normalization, and noise reduction to improve input quality. Feature extraction is performed using deep learning models such as Convolutional Neural Networks (CNN) to identify important visual patterns in hand gestures. Temporal modeling techniques including Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Transformers are used to analyze gesture sequences and understand motion over time. The recognized gestures are then converted into meaningful text or speech using Natural Language Processing (NLP). The system is capable of recognizing both simple and complex gestures with high accuracy and supports real-time or near real-time communication.
Disclaimer: Curated by HT Syndication.
