Design and Implementation of an Image to Speech Engine

Abstract

In this paper, photo electric devices and computer software are used to identify the printed characters of Optical Character Recognition (OCR). This optical character recognition will converts the images that are hand written, typed and printed text into a machine encoded text. After the process of conversion the document is scanned on an image. In research process the obtained image is converted into audio output. So the optical character recognition is nothing but a machine process which includes cognitive computing, machine translation, text to speech key data and text times. This is mainly used in the field of character recognition, computer vision and artificial intelligence. If once the recognition process is completed in OCR then the code that is generated by character will be processed by using Raspberry Pi. This Raspberry Pi device will recognize the character by using python programming and TESSERACT algorithm. After recognition an audio output is listened. At last the entire format is used in the format of grid in virtual digital library’s design and construction. In this virtual library we can perform the analysis of document image analysis (DIA) by using pattern recognition of OCR.