A Novel Vision based Finger-writing Character Recognition System

Author

Jin, Lianwen ; Yang, Duanduan ; Zhen, Li-Xin ; Huang, Jian-Cheng

Author_Institution

Sch. of Electron. & Inf. Eng., South China Univ. of Technol., Guangzhou

Volume

1

fYear

0

fDate

0-0 0

Firstpage

1104

Lastpage

1107

Abstract

A new vision based finger writing character recognition system (FWCRS) is proposed in this paper. The FWCRS allows people to write characters virtually just using his finger-tip (we call this "finger-writing"). The trajectories of the finger-tip are tracked and reconstructed as a kind of inkless character pattern and finally recognized by a classifier. In this paper, a simple but effective background model is built for the FWCRS to segment human finger from cluttered background. A robust fingertip detection algorithm based on feature matching is presented. The finger-writing character is finally recognized by a DTW classifier. Experiments show that the FWCRS can recognize finger-writing uppercase & lowercase English characters with the accuracy of 95.6%, 98.5% respectively

Keywords

computer vision; feature extraction; handwriting recognition; handwritten character recognition; image segmentation; DTW classifier; dynamic time warping; feature matching; fingertip trajectory tracking; human finger segmentation; inkless character pattern; robust fingertip detection; virtual character writing; vision finger-writing character recognition system; Character recognition; Computer vision; Digital cameras; Equations; Fingers; Human computer interaction; Pattern recognition; Robustness; Trajectory; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.145

Filename

1699082