一种鲁棒的全自动人脸特征点定位方法

A Novel Method for Robust and Automatic Facial Features Localization

人脸特征点定位的目标是能够对人脸进行全自动精确定位.主动形状模型(Active shape modal,ASM)和主动表象模型(Active appearance modal,AAM)的发表为全自动人脸特征点定位工作提供了很好的思路和解决框架.之后很多研究工作也都在ASM和AAM的框架下进行了改进.但是目前的研究工作尚未很好地解决人脸表情、光照以及姿态变化情况下的人脸特征点定位问题,本文基于ASM框架提出了全自动人脸特征点定位算法.和传统ASM方法以及ASM的改进方法的不同在于:1)引进有效的机器学习方法来建立局部纹理模型.这部分工作改进了传统ASM方法中用灰度图像的梯度分布进行局部纹理建模的方法,引入了基于随机森林分类器和点对比较特征的局部纹理建模方法.这种方法基于大量样本的统计学习,能够有效解决人脸特征点定位中光照和表情变化这些难点;2)在人脸模型参数优化部分,本文成功地将分类器输出的结果结合到人脸模型参数优化的目标函数当中,并且加入形状限制项使得优化的目标函数更为合理.本文在包含表情、光照以及姿态变化的人脸数据上进行实验,实验结果证明本文提出的全自动人脸特征点定位方法能够有效地适应人脸的光照和表情变化.在姿态数据库上的测试结果说明了本算法的有效性.

Automatic facial features localization is capable of affording accurate face location which is highly desirable for face analysis. Active shape model （ASM） and active appearance model （AAM） are efficient frameworks for facial features localization. However, the performance of these conventional methods is unsatisfactory under pose, illumination and facial expression changes. To overcome these drawbacks, an automatic and accurate facial features localization algorithm is proposed which has two improvements： 1） utilizing efficient machine learning methods （random forest classifier and paircompared feature） to construct local appearance model to deal with illumination and expression changes; 2） incorporating classifier outputs and shape constraint into the quadratic optimization. Experimental results over many images with obvious pose, expression and illumination changes have shown the accuracy and efficiency of our method.