Design and implementation of smart book reader for the blind

Abstract

This research work suggests a technique to execute an OCR based reader for the substantial number of visually debilitated. Considering how there is a large number of such people out there, we need to come up with a novel method that can be affordable as well as provides a good output. These book readers can be implemented in various ways. Here we talk around an OCR based system that is executed utilizing the product Tesseract. Later the recognized text becomes audio using TTs engines. The module utilizes a Raspberry Pi model 3B and a camera. The camera is for getting an image of the content. The image is then preprocessed before getting loaded into OCRs. The preprocessing section fuses binary images, noise removal, skew correction, division and feature extraction.