Friday 19th of April 2024
 

Feature Dimension Reduction of NaXi Pictographs Characters Recognition based on LDA


Hai Guo, Jinghua Yin and Jingying Zhao

As a kind of pictographic character, Naxi pictographs character has received little academic attention. Proposing dimension reduction method of Naxi pictographs characters on the basis of LDA (Linear Discriminant Analysis), this paper thus makes an in-depth study of feature dimension reduction, an important issue in the recognition of Naxi pictographs characters. By constructing a recognition sample library involving four features of grid feature, permeability number feature, moment invariant feature, and directional element feature (DEF), 50% of data are selected from sample library as training set and testing set respectively. Two dimension reduction methods of LDA and FA (Factor Analysis) are applied to dimension reduction experiment of features of Naxi pictographs characters. The experiment result proves LDA method to be significantly superior to FA method, as LDA method could still maintain a 99% recognition precision when the dimension is reduced to 10% of the original dimension.

Keywords: NaXi pictographs character, Linear Discriminant Analysis (LDA), Dimension reduction, features extraction, characters.

Download Full-Text


ABOUT THE AUTHORS

Hai Guo
Hai Guo born in 1979, received the M.Sc. degree (with distinction) in pattern recognition and intelligent system from the Kun Ming University of science and technology, China, in 2004. And now he works in the Department of Computer Science and Engineering of Dalian Nationalities University, Dalian, P.R.China as an associate professor. He has been interested in image processing, pattern recognition.. He has been in charge of the project of National Natural Science Foundation of China. He has published more than twenty research papers which are included in SCI, EI and so on.

Jinghua Yin
Prof. Jinghua YIN born in 1957, received his doctor¡¯s degree in Harbin Institute of Technology (HIT) in 2001. And now she works in Harbin University of Science and Technology, Harbin, P.R.China as professor and Ph.D supervisor. She is an Academic Leader of the key discipline of Heilongjiang Province as well as Harbin University of Science and Technology, an executive director of Heilongjiang Physics Society, a Distinguished Teacher of China as well as Heilongjiang Province. She has been interested in Structure and Property of Inorganic Nanohybride Films, Structure and Failure of VDMOS Devices, Packaging Structure and Reliability of Electronic Devices. She has been in charge of the project of National 863 Research Project and Natural Science Foundation of China. She has published more than sixty research papers, twenty of which are included in SCI and EI.

Jingying Zhao
Jing-ying Zhao received the M.Sc. degree (with distinction) in computer application from the Chang Chun University of science and technology, China, in 2003.She has been teaching at Dalian Nationalities University since 2003. For many years, she has done research in image processing, pattern recognition. He has published more than 20 papers.


IJCSI Published Papers Indexed By:

 

 

 

 
+++
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »