30 September 2011 Finger tips detection for two handed gesture recognition
Author Affiliations +
Proceedings Volume 8285, International Conference on Graphic and Image Processing (ICGIP 2011); 828516 (2011) https://doi.org/10.1117/12.913392
Event: 2011 International Conference on Graphic and Image Processing, 2011, Cairo, Egypt
Abstract
In this paper, a novel algorithm is proposed for fingertips detection in view of two-handed static hand pose recognition. In our method, finger tips of both hands are detected after detecting hand regions by skin color-based segmentation. At first, the face is removed in the image by using Haar classifier and subsequently, the regions corresponding to the gesturing hands are isolated by a region labeling technique. Next, the key geometric features characterizing gesturing hands are extracted for two hands. Finally, for all possible/allowable finger movements, a probabilistic model is developed for pose recognition. Proposed method can be employed in a variety of applications like sign language recognition and human-robot-interactions etc.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
M. K. Bhuyan, Mithun Kumar Kar, Debanga Raj Neog, "Finger tips detection for two handed gesture recognition", Proc. SPIE 8285, International Conference on Graphic and Image Processing (ICGIP 2011), 828516 (30 September 2011); doi: 10.1117/12.913392; https://doi.org/10.1117/12.913392
PROCEEDINGS
10 PAGES


SHARE
Back to Top