A static gesture recognition method combining depth information and skin color information

Abstract

The invention discloses a static gesture recognition method which combines depth information and skin color information. The method comprises the following steps: acquiring RGB image and depth image by kinect; using the depth threshold and human skin color information to get the binary image of the hand. Distance transform operation combined with palm cutting circle and threshold method is used tojudge whether there is arm region in hand image. The arm region is removed by exclusive OR operation between images to obtain binary gesture image. Calculating the number of Fourier descriptors and fingertips to form the eigenvector of the gesture; Support vector machine is used for gesture classification to achieve the purpose of gesture recognition. The invention realizes hand partial cutting by combining depth information and skin color information, and overcomes the influence of skin color region in complex background. By removing the arm region, the disturbance of the arm to the classification accuracy of the system can be overcome. The number of fingertips and Fourier descriptor features are computed and input to support vector machine for gesture recognition.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a static gesture recognition method combining depth information and skin color information. Background technique [0002] With the development of related technologies such as computer vision and pattern recognition, the research of human-computer interaction technology has been greatly promoted, and people can communicate with computers more naturally without being limited to keyboards and mice. Vision-based static gesture recognition, as a natural way of human-computer interaction, has gradually become a research hotspot in human-computer interaction technology, and has been widely used in smart home, robot control, sign language recognition and other fields. [0003] In static gesture recognition based on a monocular camera, it is difficult to separate the human hand from the background in the image. In the early gesture recognition systems, by wearing marked gloves ...

AI Technical Summary

Problems solved by technology

The gesture features extracted in the existing gesture recognition methods are relatively single, and the combination of multiple features can effectively improve the accuracy and robustness of gesture recognition methods

[0006] In order to achieve high classification accuracy, the classifiers selected by many gesture recognition methods take a long time and are trained on a large sample set to obtain

In addition, the speed in the classification process is slow, and it is difficult to meet the real-time requirements of the gesture recognition system

Images