MUMBAI, India, June 26 -- Intellectual Property India has published a patent application (202621051019 A) filed by Nikhil Balasaheb Kakde; Harsh Raj; Anirudh Madhunure; Moresh Mukhedkar; and Pankaj Shinde on April 21, 2026, for Handtalk Ai : Intelligent Indian Sign Language Translation System Using Opencv And Mediapipe.
Inventors include Nikhil Balasaheb Kakde; Harsh Raj; Anirudh Madhunure; Moresh Mukhedkar; and Pankaj Shinde.
The application for the patent was published on June 19, 2026, under issue no. 25/2026.
Abstract: Abstract for my project give me Here is a clean, exam-ready abstract for your project: Abstract The project titled “HandTalk AI: Intelligent Indian Sign Language Translation System using OpenCV and Machine Learning” aims to develop an efficient system that translates Indian Sign Language (ISL) gestures into readable text and speech in real time. Communication barriers between hearing-impaired individuals and others often create challenges in daily interactions, and this system addresses that issue using computer vision and artificial intelligence. The proposed system uses OpenCV for real-time hand gesture detection and preprocessing, while machine learning models such as Artificial Neural Networks (ANN) or Convolutional Neural Networks (CNN) are employed for accurate gesture classification. The system captures hand movements through a camera, extracts important features, and predicts the corresponding ISL gesture. Once the gesture is recognized, the system converts it into text and optionally into speech output, enabling effective communication. The model is trained on a dataset of ISL gestures to achieve high accuracy under normal conditions. This solution is cost-effective, user-friendly, and does not require specialized hardware, making it accessible for real-world applications in education, healthcare, and public services. Future improvements can include better performance in low-light conditions and support for continuous sentence formation.
Disclaimer: Curated by HT Syndication.
