Parameter search for an image processing fuzzy C-means hand gesture recognition system

Author

Wachs, Juan ; Stern, Helmun ; Edan, Yael

Author_Institution

Dept. of Ind. Eng., Ben-Gurion Univ. of the Negev, Beer-Sheva, Israel

Volume

3

fYear

2003

fDate

2003

Abstract

This work describes a hand gesture recognition system using an optimized image processing-fuzzy C-means (FCM) algorithm. The parameters of the image processing and clustering algorithm were simultaneously found using a neighborhood parameter search routine, resulting in solutions within 1-2% of optimal. Comparison of user dependent and user independent systems, when tested with their own trainers, resulted in recognition accuracies of 98.9% and 98.2%, respectively. For experienced users, the opposite was true, testing recognition accuracies where better for user independent than user dependent systems (98.2% over 96.0%). These results are statistically significant at the .007 levels.

Keywords

feature extraction; fuzzy systems; gesture recognition; pattern clustering; hand gesture recognition system; image processing-fuzzy C-means algorithm; parameter search routine; recognition accuracy; user independent systems; Artificial neural networks; Clustering algorithms; Communication system control; Control systems; Fuzzy systems; Image processing; Image recognition; Robot control; System testing; Telerobotics;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on

ISSN

1522-4880

Print_ISBN

0-7803-7750-8

Type

conf

DOI

10.1109/ICIP.2003.1247251

Filename

1247251