OCR BASED SPEECH SYNTHESIS SYSTEM USING LABVIEW : Text to Speech Conversion System using OCR

Abstract

Machine replication of human capacities, such as perusing, is an antiquated dream. Be that as it may, in the course of the most recent five decades, machine perusing has developed from a fantasy to reality. Discourse is likely the most proficient medium for correspondence between people. Optical character acknowledgment has turned out to be a standout amongst the best utilizations of innovation in the field of example acknowledgment and manmade brainpower. In current society, there is an awesome request to rapidly include expansive measure of printed and manually written data into the PC, along these lines everybody depend vigorously on PCs to process tremendous volumes of information. The essential goal is to enable vocally debilitated individuals to utilize the PC or to peruse archives in a simpler way. The framework is separated into two sections initially is Optical Character Recognition (OCR) and second part is content to discourse. In the initial segment, Virtual Instrument is produced in which a hued picture that contains the characters is changed over into grayscale picture and characters are prepared and in the second part; transformation from content to discourse is created. The mean of normal review time, standard deviation, least examination time and most extreme assessment time in ms is estimated. There are a few varieties in time parameters due to factors like number of characters perceived, line profile, histogram, shine, difference and gamma revision esteems.