OCR Based Speech Synthesis System Using Lab VIEW

Abstract

Knowledge extraction by just listening to sounds is a distinctive property. Although text can be a medium of communication but speech signal is more effective means of communication than text. In this thesis work OCR Based Speech Synthesis System has been discussed using LabVIEW 7.1. Although a lot of work has been done in the field OCR and Speech Synthesis individually, but it is fist OCR based Speech Synthesis System using LabVIEW. This Thesis contains two part optical character recognition and text to speech conversion. The OCR software is developed with IMAQ Vision for LabVIEW software- developing tool and it uses a commercial digital scanner as image acquisition device. IMAQ Vision OCR software is a PCbased character recognition tool for use with IMAQ Vision for LabVIEW. IMAQ Vision OCR is designed for high-speed and reliable reading performance, even with poor image quality resulting from varying lighting conditions and print quality. For speech synthesis in LabVIEW the ACTIVE X sub pallet in Communication pallet and its functions to exchange data between applications. ActiveX/COM refers to the process of controlling one program from another via ActiveX. Like networking, one program acts as the client and the other as the server LabVIEW supports ActiveX automation both as the client and the server. Both program, client and server, exist independent of each other but are able to share information. The client communicates with the ActiveX objects that the server opens to allow the sharing of information. The automation client can access the object's properties and methods. Properties are attributes of an object. This thesis aims to study the OCR and speech synthesis technology and to develop a cost effective, user friendly OCR Based Speech Synthesis System using Laboratory virtual instruments engineering workbench (LabVIEW) graphical programming language.