Vision Voice: An Assistive App for Describing Surroundings Through Image Recognition and Audio Feedback
摘要
Vision Voice is an assistive mobile application that would offer the hearing impaired a real-time audio description of surroundings. Vision Voice using image recognition and Gemini voice synthesizing system helps client to capture the images of their environment and receive feedback in English or Tamil making it easier for them to mobilize on their own. With regard to application that comprises clear and intuitive apps Layout, multilanguage support and real-time processing makes this apps very useful in enhancing accessibility. This paper outlines how Vision Voice was created, what makes it unique and the future possibilities after presenting a birds eye view of user testing and technical design.