Mahidol University Logo
Faculty of ICT, Mahidol University
 

Admissions

Printable Version

 

MY OCR

ThanyathornPatanaanunwong5088089ITCS/B
KanyaratSenapitak5088128ITCS/B
ManatsaweePhunsin5088205ITCS/B

B.Sc.(INFORMATION AND COMMUNICATION TECHNOLOGY)

Project Advisor: Dr.Sukanya Phongsusphap

Abstract

This project introduces a method of Optical Character Recognition (OCR) for camera-based document images. The system consists of five main processes: (1) Pre-Processing for noise elimination and image binarization (2) Segmentation for isolating each individual character using projection profiles (3) Feature Extraction for extracting the characteristics of character image consisting of direction of the character’s contour, density of the character’s body, and peripheral information (4) Classification using Euclidean distance classifier and (5) E-file Generation for composing each component from the previous process in the form of text file or word file. In the experiment, total 750 characters (varied sizes) have been used to test the system. The overall accuracy rate of the system is 81.07%. The result indicates that the system is efficient to some degree.

 

KEYWORDS: OPTICAL CHARACTER RECOGNITION (OCR) / IMAGE PROCESSING / CAMERA-BASED DOCUMENT IMAGE

 

Go to Top

 

ICT Building, Mahidol University, 999 Phuttamonthon 4 Road, Salaya, Nakhonpathom 73170 Tel. +66 02 441-0909 Fax. +66 02 849-6099
Mahidol University Computing Center, The Faculty of ICT, Mahidol University , Rama 6 Road, Rajathevi, Bangkok 10400 Tel. +66 02 354-4333 Fax. +66 02 354-7333