Title :
Gesture segmentation based on neural net and motion information
Author :
Wu Xiaojuan ; Jun, Yang ; Lei, Geng
Author_Institution :
Sch. of Inf. Sci. & Eng., Shandong Univ., Jinan, China
Abstract :
In this paper, a method combining skin color with motion information to detect and segment gesture in complex background is proposed. We put in RGB information of a pixel, judge the output and obtain the information that belongs to the skin area. Suppose that the hand motion is the master motion and by twice clustering, we can localize the hand. Experiment result shows this method is adaptive and robust, and can be adopted in many other research regions.
Keywords :
gesture recognition; image colour analysis; image motion analysis; image resolution; image segmentation; neural nets; RGB information; gesture segmentation; hand motion; motion information; neural net; skin color; Data mining; Feedforward neural networks; Filtering algorithms; Information analysis; Information filtering; Information filters; Information science; Neural networks; Skin; Streaming media;
Conference_Titel :
VLSI Design and Video Technology, 2005. Proceedings of 2005 IEEE International Workshop on
Print_ISBN :
0-7803-9005-9
DOI :
10.1109/IWVDVT.2005.1504605