Hand Gesture Recognition and Its Application in Robot Control

Abstract

In view of the problem that the accuracy and robustness of hand gesture recognition technology based on vision in the process of using gestures to interact with robots were unstable due to its background, illumination and other factors, this paper presented a gesture segmentation and recognition method Combining depth information and color images. First, it used Kinect sensor to obtain depth information and color images, then used depth information to pick the hand part from color images, and then got gesture images through color segmentation method. Second, it calculated HU invariant moments and shape features of the gesture images as feature information. Finally, it used the feature information to train the support vector machine, then implemented hand gesture recognition for static hand gestures. Experimental results show that the method has strong robustness to the influence of background interference, illumination variation, translation, rotation and zoom, and can be applied to control intelligent robot.