MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202641042453 A) filed by Selvanathan G, Chennai, Tamil Nadu, on April 2, for 'real time hand sign to text converter using ai and ml.'
Inventor(s) include Koushick. R; Shamili P; and Selvanathan. G M.
The application for the patent was published on May 29, under issue no. 22/2026.
According to the abstract released by the Intellectual Property India: "Communication barriers faced by hearing- and speech-impaired individuals significantly impact their ability to interact effectively with the general population. The present invention proposes an AI-based real-time sign language interpreter that integrates computer vision, machine learning, and speech synthesis into a single intelligent platform. The system utilizes vision-based hand tracking to capture and analyze hand gestures, followed by feature extraction and classification using machine learning models, including static models for American Sign Language (ASL) and sequence-based models such as Long Short-Term Memory (LSTM) for Indian Sign Language (ISL). The recognized gestures are converted into text, which is further processed to form meaningful words and sentences. The system also incorporates a text-to-speech module to generate real-time audio output, enabling effective verbal communication. A temporal consistency mechanism is implemented to enhance prediction accuracy and reduce noise. The proposed solution eliminates the need for specialized hardware and human interpreters, offering a scalable, cost-effective, and user-friendly system. Overall, the invention provides an efficient assistive communication tool that enhances accessibility and promotes inclusive interaction in real-world environments."
Disclaimer: Curated by HT Syndication.
