DocumentCode :
2710687
Title :
Incremental clustering of gesture patterns based on a self organizing incremental neural network
Author :
Okada, Shogo ; Nishida, Toyoaki
Author_Institution :
Dept. of Intell. Sci. & Technol., Kyoto Univ., Kyoto, Japan
fYear :
2009
fDate :
14-19 June 2009
Firstpage :
2316
Lastpage :
2322
Abstract :
This paper describes an incremental unsupervised clustering mechanism for sequence patterns arising from human gestures. Although self-organizing incremental neural network (SOINN) is known as a powerful tool for incremental unsupervised clustering, it is only applicable to static and fixed-length patterns. In this paper, we propose an extension to SOINN to handle dynamic sequence patterns of variable length. We use a Hidden Markov Model (HMM), as a pre-processor for SOINN, to map the variable-length patterns into fixed-length patterns. HMM contributes to robust feature extraction from sequence patterns, enabling similar statistical features to be extracted from sequence patterns of the same category. As a result of experiments with incremental clustering gesture data, we have found that HMM based SOINN (HB-SOINN) outperforms other methods.
Keywords :
data reduction; gesture recognition; hidden Markov models; learning (artificial intelligence); pattern clustering; self-organising feature maps; dynamic sequence pattern; fixed-length pattern; gesture pattern recognition; hidden Markov Model; incremental unsupervised clustering mechanism; self organizing incremental neural network; sequence data dimension reduction; unsupervised learning; variable-length pattern; Character generation; Face recognition; Feature extraction; Hidden Markov models; Humans; Motion analysis; Neural networks; Organizing; Pattern recognition; Power generation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2009. IJCNN 2009. International Joint Conference on
Conference_Location :
Atlanta, GA
ISSN :
1098-7576
Print_ISBN :
978-1-4244-3548-7
Electronic_ISBN :
1098-7576
Type :
conf
DOI :
10.1109/IJCNN.2009.5178845
Filename :
5178845
Link To Document :
بازگشت