基于层叠支持向量机的人脸检测研究

提出一种基于层叠支持向量机的人脸检测算法，用于复杂背景灰度图像的人脸检测。算法首先用线性支持向量机进行粗筛选，滤去大量非人脸窗口，之后用非线性支持向量机对通过的窗口进行分类。实验对比数据表明,该方法降低了分类器的训练难度，计算复杂度较低，大大提高了检测速度。
关键词：人脸检测，支持向量机，模式分类

Face Detection Based on Cascade Support Vector Machine QIU Xiaojia ZHAO Xiuying WANG Jikui （Luoyang College Of Technology, Luoyang 471003, Henan） Abstract：An efficient method of face detection based on cascade Support Vector Machine （CSVM）is proposed in this paper. Firstly，a LSVM coarse filter with relatively lower computational complexity is applied to the whole input image to filter out most of the non-face， then follows the NOSVM classifier to make the final decision，so the detection process is speeded
up. The experiment results show that the method can effectively detect faces under complicated background，and the processing time is shorter than using SVM alone.
Keywords：face detection，support vector machine，pattern classification