English Character Recognition of an Image and Voicing System

Abstract

attached

In this research, an attempt has been made to develop a recognition strategy for printed English character (A to Z) to help visually impaired people to overcome their disability in reading. Images in specific formats such as JPEG, BMP, JPG etc. were took as input images. Then the noise which comes to the image in acquisition was filtered. After that the coloured image was converted to a binary image using a suitable threshold. Then segmentation technique was used to identify connected areas while bounding boxes were used to identify individual letters. Finally recognition was done using a Statistical algorithm which uses a pre stored example database. Database is a collection of English alphabet letters saved as images. Apart from the recognition a complete system of image acquisition and a text to voice conversion strategy was developed to make the system more useful which helps visually impaired person to understand a the context of a writing.