Hand posture classification using wavelet moment invariant

Author

Sribooruang, Y. ; Kumhom, P. ; Chamnongthai, K.

Author_Institution

Dept. of Electron. & Telecommun. Eng., King Mongkut´´s Univ. of Technol., Bangkok, Thailand

fYear

2004

fDate

12-14 July 2004

Firstpage

78

Lastpage

82

Abstract

In this paper, we present a wavelet moment invariants for classification a small change in rotation and subtle difference of hand posture causes misclassifying to other postures. The method combined zernike moment to capture global features and wavelet moment to differentiate between subtle variations in description can be utilized at the same time. Then, a fuzzy classification algorithm is used to classify hand posture. The classification rate obtained is 72% with of Thai sign language.

Keywords

Zernike polynomials; feature extraction; gesture recognition; image classification; method of moments; wavelet transforms; Thai sign language; feature extraction; fuzzy classification algorithm; hand posture classification; hand rotation; image classification; wavelet moment invariant; zernike moment; Application software; Computer science; Fingers; Handicapped aids; Histograms; Human computer interaction; Principal component analysis; Robots; Shape; Virtual reality;

fLanguage

English

Publisher

ieee

Conference_Titel

Virtual Environments, Human-Computer Interfaces and Measurement Systems, 2004. (VECIMS). 2004 IEEE Symposium on

Print_ISBN

0-7803-8339-7

Type

conf

DOI

10.1109/VECIMS.2004.1397192

Filename

1397192