MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541112533 A) filed by Sini Prabhakar; M. Vishnu Ram; S. Sri Ragavendhira; P. Yogesh; and S. Sanjaykumar, Coimbatore, Tamil Nadu, on Nov. 17, 2025, for 'real time vision based sign language recognition using mediapipe & cnn.'
Inventor(s) include M. Vishnu Ram; S. Sri Ragavendhira; P. Yogesh; and S. Sanjaykumar.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The invention provides a real-time vision-based system for recognizing sign language gestures using deep-learning and computer-vision techniques. The system .employs MediaPipe for hand detection and landmark extraction, followed by a Convolutional Neural Network (CNN) that classifies gestures into corresponding alphabets or words. Live video captured from a standard webcam is preprocessed, the hand region isolated, and key features extracted for model inference. The recognized gesture is displayed as on-screen text or voice output, enabling seamless communication between hearing- and speech-impaired users and others. The platform offers high accuracy, real-time responsiveness, and hardware independence, making it suitable for educational, assistive, and public-interaction applications."
Disclaimer: Curated by HT Syndication.
