基于SVM的三阶段人脸检测方法的研究与应用

Research and Application about Three-Stage Face Detection Method Based on SVM

为了提高人脸的检测速度,描述了一种基于SVM的三阶段人脸检测方法,加速了复杂背景下人脸的检测。在该方法中,通过前两个阶段的瀑布型分类器将大量的简单非人脸模块快速过滤掉,并在最后的第三个阶段采用了非线性SVM分类器来更高效地区分24*24像素的人脸或者非人脸图像。

In this paper,present a three- stage method to speed up an SVM- based face detection system. In this proposed system, a large number of simple non - face patterns are rejected quickly by two first stage cascaded classifiers using flexible sizes of analyzing Windows while the last stage uses a non linear SVM classifier to robustly classify complex 24 ＊ 24 pixel patterns as either faces or non - faces.