MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122149 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'real-time sign language recognition system using deep learning.'
Inventor(s) include Dr. Krishnaraj Natarajan; Ms. Aditi Agarwal; and Mr. Devansh Bhargava.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a method (100) for real-time sign language recognition. The method (100) includes capturing 5 video frames from a camera in step (102), detecting hand regions using computer vision in step (104), extracting spatial information representing hand configuration from detected hand regions in step (108), generating a standardized representation that reduces environmental noise in step (110), classifying the hand gesture using a trained machine learning 10 model in step (112), and outputting the recognized gesture in step (114). The method uses MediaPipe hand tracking technology to identify hand regions and extracts twenty-one hand landmark points (21). The standardized representation creates a skeletal representation on a white background, and the trained machine learning model includes a convolutional neural network configured to process the 15 standardized representation."
Disclaimer: Curated by HT Syndication.
