| 摘要: |
| 给出一种基于表观的动态孤立手势识别技术.借助于图像运动的变阶参数模型和鲁棒回归分析,提出一种基于运动分割的图像运动估计方法.基于图像运动参数,构造了两种表观变化模型分别作为手势的表观特征,利用最大最小优化算法来创建手势参考模板,并利用基于模板的分类技术进行识别.对120个手势样本所做的大量实验表明,这种动态孤立手势识别技术具有识别率高、计算量小、算法稳定性好等优点. |
| 关键词: 计算机视觉,人机接口,手势识别,图像运动模型,鲁棒回归,动态规划匹配. |
| DOI： |
| 分类号: |
| 基金项目:本文研究得到国家863高科技项目基金(No.863-306-03-01)资助. |
|
| Appearance-Based Dynamic Hand Gesture Recognition from Image Sequences with Complex Background |
|
ZHU Yuan-xin,XU Guang-you,HUANG Yu
|
| Abstract: |
| In this paper, the authors present an appearance-based approach to dynamic hand gesture recognition. A motion-based segmentation scheme for image motion estimation is proposed using variable-order parameterized models of image motion and robust regression. Based on image motion parameters, two different appearance change models of hand gestures are created. Template-Based classification technique is then employed to perform hand gesture recognition in which reference templates are created with a mini-max type of optimization. A series of experiments on 120 image sequences show that high recognition rate, low computation load, and high stability can be achieved with the proposed methods. |
| Key words: Computer vision, human computer interface, hand gesture recognition, image motion model, robust regression, dynamic programming matching. |
