| Active Appearance Model Based Hand Gesture Recognition |
| |
| 作者姓名： | 滕晓龙 于威威 刘重庆 |
| |
| 作者单位： | Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai 200030 |
| |
| 摘 要： | This paper addresses the application of hand gesture recognition in monocular image sequences using Active Appearance Model （AAM）, For this work, the proposed algorithm is composed of constricting AAMs and fitting the models to the interest region. In training stage, according to the manual labeled feature points, the relative AAM is constructed and the corresponding average feature is obtained. In recognition stage, the interesting hand gesture region is firstly segmented by skin and movement cues. Secondly, the models are fitted to the image that includes the hand gesture, and the relative features are extracted. Thirdly, the classification is done by comparing the extracted features and average features. 30 different gestures of Chinese sign language are applied for testing the effectiveness of the method. The Experimental results are given indicating good performance of the algorithm.
|
| 关 键 词： | 模式识别 人机交互作用 手势识别 手语 AAM 图像序列 |
| 收稿时间： | 2004-09-15 |
Active Appearance Model Based Hand Gesture Recognition |
| |
| TENG Xiao-long,YU Wei-wei,LIU Chong-qing.Active Appearance Model Based Hand Gesture Recognition[J].Journal of Donghua University,2005,22(4):67-71. |
| |
| Authors: | TENG Xiao-long YU Wei-wei LIU Chong-qing |
| |
| Abstract: | This paper addresses the application of hand gesture recognition in monocular image sequences using Active Appearance Model (AAM). For this work, the proposed algorithm is composed of constructing AAMs and fitting the models to the interest region. In training stage, according to the manual labeled feature points, the relative AAM is constructed and the corresponding average feature is obtained. In recognition stage, the interesting hand gesture region is firstly segmented by skin and movement cues. Secondly, the models are fitted to the image that includes the hand gesture, and the relative features are extracted. Thirdly, the classification is done by comparing the extracted features and average features. 30 different gestures of Chinese sign language are applied for testing the effectiveness of the method. The Experimental results are given indicating good performance of the algorithm. |
| |
| Keywords: | human-machine interaction hand gesture recognition AAM sign language |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
