Published Paper Details:

This research addresses the challenges faced by visually impaired individuals in recognizing people, interpreting facial expressions, and engaging in social activities. Current visual implant systems, like the RPS, suffer from low resolution phosphene images, limiting their effectiveness in artificial vision solutions. To overcome these limitations, our project introduces a pioneering VT-based approach, adapting a deep learning architecture for natural image recognition. Our innovative method utilizes the VT to extract and process crucial information from the user's surroundings. By comprehending the visual environment, this system provides enhanced perception for visually impaired individuals, offering insights into count, familiarity, gender, estimated ages, facial emotions, surrounding objects, and approximate distances of individuals nearby. The integration of the VT into the artificial vision system aims to transcend the constraints of current technologies, providing visually impaired individuals with a transformative tool. This research not only contributes to the advancement of artificial vision but also has the potential to significantly enhance the quality of life for those with visual impairments.