Face Detection Algorithm Based on Haar and Local Binary Pattern Features

Face detection is one of the hottest research topics of the field of pattern recognition, image processing, machine vision, and etc. This paper proposes a novel method for fast and reliable face detection, especially in complex background. Firstly, the Haar features of the training image are extracted, and then the training image is divided into small blocks to extract local binary pattern (LBP) features. Secondly, the Haar and LBP features are combined together to ensure the classification capability of Haar features and the short detection time provided by reducing the dimension of LBP. Finally, the fused features are trained to get a classifier for face detection. Experimental results show that our method outperforms the methods that are based on Haar features or LBP features individually.