Title :
A symbol grounding problem of gesture motion through a self-organizing network of time-varying motion images
Author :
Mukai, Toshiro ; Nishimura, Takuichi ; Endo, T. ; Oka, Ryuichi
Author_Institution :
Tsukuba Res. Center, Ibaraki, Japan
Abstract :
We applied a method for self-organizing a network to gesture motion images. We extract both so-called common parts and singular parts of gesture by analysis of the network topology. We propose a method to extract elemental motion units from gesture motion images. We propose the gesture recognition method of a large vocabulary on the basis of recognition of the elemental motion units
Keywords :
computer vision; feature extraction; image sequences; motion estimation; network topology; self-organising feature maps; elemental motion units; feature extraction; gesture motion images; gesture recognition; image sequences; incremental path method; network topology; self-organizing network; symbol grounding problem; time-varying motion images; Grounding; Hidden Markov models; Humans; Image sequences; Man machine systems; Network topology; Self-organizing networks; Speech recognition; Target recognition; Vocabulary;
Conference_Titel :
Fuzzy Systems Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4863-X
DOI :
10.1109/FUZZY.1998.687577
