Static Hand Gesture Recognition Based on HOG with Kinect

In this paper, we propose and implement a novel method for recognition static hand gestures using depth data from Kinect sensor of Microsoft. Compared to the entire human body, the hand is a smaller object with more complex articulations and more easily affected by segmentation errors. So it is a very challenging problem to recognize hand gestures. Our approach involves choosing HOG feature with both geometric moment invariant features and adapted to the light transform by analyzing the features of hands characteristics. Through the rapid cascade Adaboost training algorithm obtains the training models of gestures and matches them, thus build the accuracy and efficiency hand gesture recognition system using the Kinect sensor.