Hand posture recognition in video using multiple cues

Liang Sha, Guijin Wang, Anbang Yao, Xinggang Lin, Xiujuan Chai

Abstract

Hand posture conveys profound information for computer vision applications, but the articulated hand structure and restraint capture condition cast a tough obstacle on practical implementation, especially in real time video. This paper presents a framework to recognize hand postures in consecutive video frames. Mixture of Gaussian skin/non skin models is constructed for hand region detection, followed by particle filter to track hand. Then a soft-decision scheme based on extended Histogram of Orientated gradient is proposed to refine the best posture region and recognize it from pre-defined posture set. Experimental result shows promising performance under various capture conditions.
BibTeX
@inproceedings{sha2009hand,
  author = {Liang Sha and Guijin Wang and Anbang Yao and Xinggang Lin and Xiujuan Chai},
  title = {{Hand posture recognition in video using multiple cues}},
  booktitle = {ICME},
  year = {2009},
  doi = {10.1109/icme.2009.5202637},
}

Loading related content...

Figure