OCR based facilitator for the visually challenged

This paper proposes a novel implementation of an Optical Character Recognition (OCR) based smart book reader for the visually challenged. There is a need for a portable text reader that is affordable, portable and readily available to the community. We propose a camera based framework built on the Raspberry Pi, integrated with Image processing algorithms, OCR and Text-to-Speech (TTS) synthesis module. The camera module is used to capture an image of the printed text, and the image is then subject to preprocessing before being fed into the OCR. The preprocessing stage includes binarization, de-noising, deskewing, segmentation and feature extraction. This paper addresses the integration of a complete Text Read-out system designed for the visually challenged. The OCR used in this project is Google Tesseract and the TTS employed is Pico.