Recognising moving hand shapes

Author

Holden, Eun-Jung ; Owens, Robyn

Author_Institution

Sch. of Comput. Sci. & Software Eng., Univ. of Western Australia, Crawley, WA, Australia

fYear

2003

fDate

17-19 Sept. 2003

Firstpage

14

Lastpage

19

Abstract

The paper presents a new hand shape representation technique that characterises the finger-only topology of the hand, by adapting an existing technique from speech signal processing. From a moving hand sequence, the tracking algorithm determines the centre of the largest convex subset of the hand, using a combination of pattern matching and condensation algorithms. A hand shape feature represents the topological formation of the finger-only regions of the hand using a linear predictive coding parameter set called cepstral coefficients. Experimental results demonstrate the effectiveness of detecting the shape feature from motion sequences.

Keywords

feature extraction; gesture recognition; image motion analysis; image sequences; linear predictive coding; object recognition; optical tracking; pattern matching; topology; cepstral coefficients; condensation algorithm; convex subset; finger-only topology; hand gesture recognition; hand shape representation; linear predictive coding parameter set; motion sequences; moving hand shape recognition; pattern matching; shape feature detection; speech signal processing; tracking algorithm; Autocorrelation; Cepstral analysis; Feature extraction; Linear predictive coding; Pattern matching; Pixel; Shape; Signal processing algorithms; Speech recognition; Topology;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Processing, 2003.Proceedings. 12th International Conference on

Print_ISBN

0-7695-1948-2

Type

conf

DOI

10.1109/ICIAP.2003.1234018

Filename

1234018