|
DSpace@UM >
Faculty of Computer Science and Information Technology >
Conference Proceedings >
International Conference on Informatics >
Informatics 2007 >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1812/353
|
|
| Title: | A STUDY ON NORMALIZATION AND FEATURE EXTRACTION TECHNIQUES FOR THE RECOGNITION OF ISOLATED KANNADA HANDWRITTEN NUMERALS |
| Authors: | Surekha Patil
Meenakshi Patil |
| Keywords: | Handwritten numeral recognition
Normalization
Aspect ratio
Direction features
Gradient features |
| Issue Date: | 2007 |
| Abstract: | The evaluation of various techniques is important to select the correct options in developing character recognition
system. Normalization is an important preprocessing technique for character recognition and feature extraction is the
core of OCR. In this paper we conduct experiments for different normalization functions and different feature extraction
strategies. It is hoped that this study improves the performance of character recognition system and will find wider use
to the researchers. |
| Description: | Proceeding of the 2nd International Conference on Informatics (Informatics 2007), 27th-28th November 2007, Hilton Petaling Jaya Hotel, Petaling Jaya, Selangor, Malaysia. Page T1-105 - T1-109 |
| URI: | http://dspace.fsktm.um.edu.my/handle/1812/353 |
| ISBN: | 978-983-43491-1-0 |
| Appears in Collections: | Informatics 2007
|
This item is protected by original copyright
|
|
