Title :
Hand detection based on self-organizing map and motion information
Author :
Wu, Xiuojuan ; Xu, Liqun ; Boyang Zhang ; Ge, Qingguo
Author_Institution :
Inst. of Information Sci. & Eng., Shandong Univ., China
Abstract :
In this paper, a method combining SOM-color clustering and motion information is presented. This method can detect and segment dynamic hand gesture in complex background. Through HSV vector and the improved conventional SOM, the number of color clusters can be determined and color can cluster automatically. Experimental results show the proposed dynamic gesture detection and segmentation algorithm is adaptive, fast and robust. And this method can also be adopted in other research region.
Keywords :
image colour analysis; image motion analysis; image segmentation; object detection; pattern clustering; self-organising feature maps; color clustering; gesture detection; hand detection; hand gesture; image segmentation algorithm; motion information; self-organizing map; Clustering algorithms; Feature extraction; Hidden Markov models; Human computer interaction; Image segmentation; Information science; Lighting; Motion analysis; Motion detection; Robustness;
Conference_Titel :
Neural Networks and Signal Processing, 2003. Proceedings of the 2003 International Conference on
Conference_Location :
Nanjing
Print_ISBN :
0-7803-7702-8
DOI :
10.1109/ICNNSP.2003.1279259
