浅谈手势识别在人机交互中的应用

The Application of Hand Gesture Recognition in Human Computer Interaction

为满足人机交互系统中手势识别的需要,提出了一种基于视觉的多点手势识别方法及其人机交互技术框架,利用USB摄像头获取手势图像,采用自适应阈值二值化法进行手势分割,再通过空间向量模型得到特征向量,最后用隐马尔可夫模型进行识别,实验结果表明,该手势识别法在人机交互中的应用是可行的且性能稳定。

To satisfy the demands of hand recognition in computer interaction system,A framework of human-computer interaction based on multi-point gesture recognition is presented,the Method uses USB camera to obtain a gesture image and Adaptive threshold Two-val ue method to handle gesture segmentation,and then it get the feature vector through the vector space model,finally HMM is used as repre sentations for hand gesture recognition,The experiments showed that the algorithm for dynamic gestures was feasible and its performance was stable.the vector space model to.