The Feature Vector Selection for Robust Multiple Face Detection

Abstract

This paper presents the robust feature vector selection for multiple frontal face detection based on the Bayesian statistical method. The feature vector for the training and classification are integrated by means, amplitude projections, and its 1D Harr wavelet of input image. And the statistical modeling is performed both for face and nonface classes. Finally, the estimated probability density functions (PDFs) are applied by the proposed Bayesian method to detect multiple frontal faces in an image. The proposed method can handle multiple faces, partially occluded faces, and slightly posed-angle faces. Especially, the proposed method is very effective for low quality face images. Experiments show that detection rate of the propose method is 98.3% with three false detections on SET3 testing data which have 227 faces in 80 images.