Improved Face Detection Using Spatial Histogram Features

In this paper, we improve an object detection approach using spatial histogram features, by applying classifier ensemble. The spatial histogram features can preserve texture and shape information of an object, simultaneously. We train a hierarchical classifier by combining cascade histogram matching and the combination of Multi Layer Perceptrons. The cascade histogram matching is trained via automatically selected discriminative features. A forward sequential selection method is presented to construct uncorrelated and discriminative feature sets for combination of MLPs and RBFs. We evaluate the proposed approach on face objects. Experimental results show that the proposed approach is efficient and robust in object detection.