| 基于光流的动态手势识别 |
| |
| 引用本文： | 刘江华,程君实,陈佳品.基于光流的动态手势识别[J].计算机工程,2002,28(4):104-105. |
| |
| 作者姓名： | 刘江华 程君实 陈佳品 |
| |
| 作者单位： | 上海交通大学信息存储中心,上海,200030 |
| |
| 摘 要： | 手势识别是人机交互中的重要组成部分，文章针对基于光流PCA（主分量分析）和DTW（动态时间规整）进行命令手势识别。利用块相关算法计算光流，并通过主分量分析得到降维的投影系数，以及手掌区域的质心作为混合特征向量。针对该混合特征向量定义了新的加权距离测度，并用DTW对手势进行匹配。针对9个手势训练和识别，识别率达到92％。
|
| 关 键 词： | 动态手势识别 光流 主分量分析 动态时间规整 语音识别 神经网络 计算机 |
| 文章编号： | 1000-3428(2002)04-0104-02 |
| 修稿时间： | 2001年7月6日 |
Dynamic Hand Gesture Recognition Based on Optical Flow |
| |
| LIU Jianghua,CHENG Junshi,CHEN Jiapin.Dynamic Hand Gesture Recognition Based on Optical Flow[J].Computer Engineering,2002,28(4):104-105. |
| |
| Authors: | LIU Jianghua CHENG Junshi CHEN Jiapin |
| |
| Abstract: | Hand gesture recognition is an important component of human-computer interaction. This paper recognizes command gesture-based optical flow PCA (principle component analysis) and DTW (dynamic time warping). Optical flow is computed with block relative algorithm, and then processed with PCA to form low-dimensional projection coefficients. The coefficients are combined with the center position of hand as mixed feature vector. A new weighted distance is defined for this mixed vector, which is then used in DTW for hand gesture matching. The recognition rate on 9 gestures is 92%. |
| |
| Keywords: | Gesture recognition Optical flow Principle component analysis Dynamic time warping |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
