Object Detection for Visually Challenged Using Image Processing

Abstract

Recent studies have demonstrated the potential of visual interventions to improve the functioning of visually impaired patients. Therefore, clarification of the profile of visual defects and possible mechanisms underlying these defects are needed. Therefore, advanced methods are required for the problem and this can involve the usage of OCR, face recognition, and sign to speech technology. The predicted output will be converted to audio using text to speech API. The main output is exhibited in a user interface which is made to scan the surroundings periodically and provide assistance.