Audio Based Line Tracing Feedback with Handsight for Low Vision Users

Abstract

Accessing printed text like papers, text books is a major challenge for the visually impaired people. In this paper an efficient innovative and real-time cost beneficial technique that enables user to hear the contents of text images instead of reading through them has been introduced. It includes the concept of Optical Character Recognition (OCR) and Text to Speech Synthesiser (TTS) in Raspberry pi board. This kind of system helps low vision users to interact with people effectively through vocal interface. Text Extraction from normal text and colour images is a difficult task in computer vision. Text-to-Speech synthesizer is a device that scans and reads English alphabets and numbers that are in the text image using OCR technique and changing it into vocal interface. This paper describes the design, implementation and experimental results of the device. This device consists of two modules, processing of image and processing of voice. The device was developed based on Raspberry Pi 3 with 1.2 GHz processor speed. The software platforms used are Raspbian Operating System, Python software language.