Design and Implementation of Smart Glove for Visually Impaired People

• Main Authors: Jayachitra, J., Muthulakshmy, S., Kumar, M.Arun, Elavarasi, K.
• Format: Conference Proceeding
• Language: English
• Subjects: Cameras; Color; Deep learning; Deep Neural Network; Merging; Micro-Vibrating Motors; Neural networks; Real-time systems; Smart Glove; Universal Serial Bus; yolov5
• ISSN: 2832-3017
• DOI: 10.1109/ICSSIT55814.2023.10061070

The visually handicapped have a difficult time locating things of everyday use because of their impairment. With the use of Deep Neural Networks (DNN) and YOLO version 5, the purpose of this study is to develop a smart glove with the intention of directing the hand of a person who is vision impaired to the desired object while the individual is inside. The micro-vibrating motors included within the smart glove are designed to direct the user's hand. The palm of the glove has a camera that connects to a Universal Serial Bus (USB), and this camera sends real-time footage to the system so it can be processed. Additionally, it includes a camera and a microphone integrated right into it. The user issues audio commands to the system, telling it to identify the item of their choosing. After that, the camera employs DNN in order to detect the item. The process of tracking the object will start after it has been tagged. The micro-vibrating motors vibrate in a manner that is proportional to the relative location of the camera in relation to the object in order to steer the user's hand in the desired direction. The ability to differentiate between identical items based on colour is an extra capability that has been introduced.