基于支持向量机和决策融合的人脸检测  

Face Detection Based on SVMs and Decision Fusion

作　　者：祝磊[1] 朱善安[1] 

机构地区：[1]浙江大学电气工程学院,杭州310027

出　　处：《科技通报》2006年第6期846-850,共5页Bulletin of Science and Technology

摘　　要：针对灰度图像中的人脸检测问题,提出了一种基于多种支持向量机的决策融合检测方法。该方法首先用传统的二类支持向量机(C—SVM)和单类支持向量机(One-Class SVM)分别对图像进行检测,然后决策融合两种分类器的检测结果。在MIT+CUM人脸库上的实验结果表明,该方法具有良好的检测效果和较低的虚警率。In this paper, a face detection method based different SVMs and decision fusion is proposed. C-SVM and OCSVM （One-Class SVM） are used as classifiers to search the whole picture respectively. Then fusion decision is adopted to get the final results of face detection. To test our algorithm＇s performance, a series of experiments were performed on MIT＋CUM image databases. The results show that the proposed method has encouraging performance.

关 键 词：人脸检测 支持向量机 单类支持向量机 模式识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]