Sign Vista

Abstract

The advancement of gesture-based communication systems, especially in the context of American Sign Language (ASL), calls for innovative solutions that bridge the communication gap for the hearing-impaired community. Our project, SignVista, presents a mobile application that translates ASL gestures into text in real-time. Leveraging machine learning techniques, specifically Random Forest classifiers, our system accurately recognizes hand gestures from real-time camera input, converting them into corresponding text outputs. SignVista’s core features include a user-friendly interface, gesture-to-text conversion, and an offline mode for accessibility. The system is designed with scalability in mind, allowing for future integration with other sign languages and the inclusion of more gestures. By enhancing communication efficiency, SignVista holds potential for improving everyday interactions for ASL users in various public and private settings. Our project aims to provide a practical, easy-to-use tool that empowers the hearing-impaired community with advanced translation capabilities, all while ensuring reliable, accurate performance across different devices