Pattern Recognition Based on Relative Position of Local Features Using Self-Organizing Map

Author

Horio, Keiichi ; Aikawa, Akira ; Yamakawa, Takeshi

Author_Institution

Graduate Sch. of Life Sci. & Syst. Eng., Kyushu Inst. of Technol.

Volume

2

fYear

2006

fDate

Aug. 30 2006-Sept. 1 2006

Firstpage

293

Lastpage

296

Abstract

In this paper, we propose a new pattern recognition method based on relative position of local feature. In the visual system of human, the local features such as lines and curves are extracted, and they are integrated. In the proposed method, relative position of the gazing points which include local features are extracted using self-organizing map. A template matching concerning the local features is used for recognizing the patterns. The effectiveness of the proposed method is verified by applying it to MNIST handwritten digits database

Keywords

feature extraction; image matching; image recognition; self-organising feature maps; gazing points; image recognition method; local feature extraction; local feature relative position; pattern recognition; self-organizing map; template matching; Feature extraction; Humans; Image edge detection; Image recognition; Neural networks; Pattern matching; Pattern recognition; Spatial databases; Visual databases; Visual system;

fLanguage

English

Publisher

ieee

Conference_Titel

Innovative Computing, Information and Control, 2006. ICICIC '06. First International Conference on

Conference_Location

Beijing

Print_ISBN

0-7695-2616-0

Type

conf

DOI

10.1109/ICICIC.2006.329

Filename

1691984