MUMBAI, India, Nov. 28 -- Intellectual Property India has published a patent application (202531106400 A) filed by Jis College Of Engineering, Kalyani, West Bengal, on Nov. 3, for 'hand speak: computer vision powered sign language translator.'
Inventor(s) include Mr. Tushar Ghorui; Ms. Sukanya Das; Dr. Suparna Das Gupta; Dr. Soumyabrata Saha; Dr. Jayanta Pal; and Dr. Srabani Biswas.
The application for the patent was published on Nov. 28, under issue no. 48/2025.
According to the abstract released by the Intellectual Property India: "The present invention relates to a real-time, automated system for translating sign language gestures into speech using computer vision and deep learning techniques. The system captures hand gestures through a standard webcam and processes them using OpenCV-based image preprocessing algorithms to detect and isolate the region of interest. A hybrid deep learning model, combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks, is employed to accurately recognize and classify sign language gestures based on spatial and temporal features. The recognized gestures are mapped to corresponding text and subsequently converted into natural-sounding speech using Google Text-to-Speech (GTTS) technology. Unlike conventional systems that rely on expensive hardware such as motion sensors or gloves, this invention functions entirely through a standard camera, making it affordable, portable, and accessible. The system is scalable to support multiple sign languages and adaptable for deployment on various platforms, including computers, mobile devices, and wearable technologies. This invention enhances communication between hearing-impaired individuals and non-sign language users, promoting inclusivity, accessibility, and independence in social and professional interactions."
Disclaimer: Curated by HT Syndication.
