Volume 2 - Issue 1, January - February 2026

Communication between hearing-impaired individuals and the general public is often challenging because many people are unfamiliar with sign language. This project presents an assistive system that converts hand gestures into readable text using machine learning and computer vision techniques. The system captures hand gestures through a standard camera and processes them using real-time hand landmark detection. Instead of analyzing full images, the system extracts important hand key points and converts them into numerical features. These features are then provided to a trained machine learning classifier to recognize gestures representing common words or expressions. The predicted output is displayed as text on the screen instantly, enabling smooth and natural interaction. The proposed solution is simple, cost-effective, and user-friendly, as it requires no special hardware other than a camera. It can be effectively used in educational institutions, public service environments, and assistive communication applications. By translating visual gestures into text automatically, the system reduces dependence on human interpreters and promotes independent communication. The system is designed to operate under varying lighting conditions and different backgrounds, making it suitable for real-world scenarios. Furthermore, it can be extended in the future to support a larger vocabulary, continuous sentence formation, and integration with mobile or web-based platforms. Overall, this project demonstrates the practical potential of artificial intelligence in creating inclusive technologies and improving accessibility for the hearing-impaired community.

Afsana Khan Patan, Drakshavali Guttikanti, Nithish Gaddala, Vaishnavi Muppavarapu, Sarnapati Charan Kumar,"Sign Language Detection Using Hand Landmark-Based Machine Learning" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(1): Page(1431-1436) Jan-Feb 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.