Bare Hand Gesture Recognition with a Single Color Camera

A bare hand gesture recognition system using only a single color camera without any marker is presented in this paper. The system is mainly composed of image pre-processing, skin segmentation, feature extraction and gesture classification. The image pre-processing module transforms the raw image into the desirable feature vector which mainly includes converting the color images into the hue images and reducing noise. The skin segmentation module localizes and segments the skin region from the whole image and eliminates the forearm region with the help of a wrist line. The feature extraction module extracts a set of distinct parameters to represent each gesture and distinguish the different gestures. To verify the performance of the designed system, the interaction game of scissors, rock and paper was played between the computer and users, and the application results indicate that the system could reach to a recognition rate of bare hand gestures 93.1% in the complex environment conditions.