基于离散隐马尔可夫模型和奇异值特征的人脸检测

Face Detection Based on Discrete Hidden Markov Models and Singular Value Feature

该文提出了基于离散隐马尔可夫模型 (HMM )和奇异值特征的人脸检测方法。这一算法包含 2部分工作。首先 ,提出了基于离散隐马尔可夫模型和奇异值特征的正面端正人脸检测方法 ;然后将该算法扩展到检测任意旋转角度的人脸。扩展算法首先计算当前位置子图像窗口的奇异值特征 ,将该特征向量经过识别各个旋转角度人脸的HMM模型 ,得到该子图像窗口的旋转角度 ,再经过旋正 ,重新送到识别正面端正人脸的HMM模型 ,由此确定该子图像窗口是否为人脸。对一个由 43幅集体照片组成的正面人脸图像集进行测试 ,共检测到 484人中的 42 5人 ,检测率为 87.8% ;而多角度旋转人脸图像检测率为 75 .1%。实验结果表明 。

This paper presents a novel face detection method which consists of two algorithms. The first one is a frontal view upright face detection algorithm based on the well known singular value feature (SVF) and discrete hidden Markov models (HMM). The algorithm couples the virtues of both the SVF and HMM and produces excellent detection results. It is tested on a collective photo album and has detected the 87.81 percent of its 484 people, while 537 false alarms are reported. The second one is the extension of the first one to rotation invariant face detection. Several HMMs are utilized simultaneously and the angle of the ‘face’ image is obtained. Then the HMM for detecting the upright faces is employed to verify the faceness of the test pattern. This rotation invariant algorithm is tested on another image set of 173 persons and the detection rate is 75.14 %.