Practical study on real-time hand detection

Abstract

In this paper we describe algorithms and image features that can be used to construct a real-time hand detector. We present our findings using the Histogram of Oriented Gradients (HOG) features in combination with two variations of the AdaBoost algorithm. First, we compare stump and tree weak classifier. Next, we investigate the influence of a large training database. Furthermore, we compare the performance of HOG against the Haar-like features.