Smart Glasses: A Visual Assistant for the Blind

Abstract

Computer vision has helped systems gain high-level understanding in the field of image and video processing. The Smart Glasses allows partially blind and partially sighted individuals to identify and understand the workplace tools that surround them, which they can see through mini camera. Our research aims to utilize the computer vision to detect objects using MS COCO dataset and trained a CNN (Convolutional Neural Network) model. It recognizes faces using deep learning approach. It recognizes text using EAST (Efficient Accurate Scene Text Detector) and EASYOCR models and gives output using Festival Speech synthesis. The glasses are provided by Ultrasonic sensor which is used to measure the required distance between the users and object to avoid obstacle. The Smart glasses start detecting using the wake word “UP” which is trained using CNN and TensorFlow and Vosk speech recognition module for simple commands. The system is a complete visual assistance for the blind.