SVM classifier based face detection system using BDIP and BVLC moments

In this paper, a support vector machine (SVM) classifier has been used to detect a face in an authentication application. A face candidate is first allocated from the input frame and then normalized to 200×200 pixels images. The textureness of candidates is then measured by the combination of BDIP and BVLC moments and classified into face and non-face ones by a SVM classifier which is known as efficient classification tool. In SVM learning, a DB of 2500 faces and 2500 non-faces has been created under different light conditions and face expressions. The experiments showed that the effectiveness of the used features for SVM based classification issue in the face-detection system.