Human face detection algorithm via Haar cascade classifier combined with three additional classifiers

Human face detection has been a challenging issue in the areas of image processing and patter recognition. A new human face detection algorithm by primitive Haar cascade algorithm combined with three additional weak classifiers is proposed in this paper. The three weak classifiers are based on skin hue histogram matching, eyes detection and mouth detection. First, images of people are processed by a primitive Haar cascade classifier, nearly without wrong human face rejection (very low rate of false negative) but with some wrong acceptance (false positive). Secondly, to get rid of these wrongly accepted non-human faces, a weak classifier based on face skin hue histogram matching is applied and a majority of non-human faces are removed. Next, another weak classifier based on eyes detection is appended and some residual non-human faces are determined and rejected. Finally, a mouth detection operation is utilized to the remaining non-human faces and the false positive rate is further decreased. With the help of OpenCV, test results on images of people under different occlusions and illuminations and some degree of orientations and rotations, in both training set and test set show that the proposed algorithm is effective and achieves state-of-the-art performance. Furthermore, it is efficient because of its easiness and simplicity of implementation.