基于多角度LBP特征的三维人脸性别分类

3D Facial Gender Classification Based on Multi-angle LBP Feature

人脸性别分类是一个富有挑战的研究方向,目前的研究尚不完善.本文提出一种三维人脸的性别分类方法,首先对数据集进行局部区域最近邻点迭代算法(Iterative closest point,ICP)匹配,自动实现人脸正向姿态校正;对数据集人脸统一做俯仰角度的旋转,从不同视角上提取基于深度缩略图的多角度LBP(Local binary patterns)特征;再由支持向量机(Support vector machine,SVM)分类器完成训练分类.该方法在CASIA数据库上实验,对全库中性表情人脸进行性别分类,可以得到最高98.374%的正确率.

Facial gender classification is a challenging topic, and it＇s still not perfect until now. In this paper, we propose a se- ries of methods of gender classification based on three-dimension faces. Automatic front-pose adjustment is needed through local region iterative closest point （ICP） registration firstly; then we do pitching rotating and extract multi-angle LBP features from depth thumbnail map in different viewing angles; at last, we use support vector machine （SVM） classifier to do training and prediction. This algorithm has been experimented on CASIA database, and for the neutral faces in this database, we can get a highest correct classification rate of 98.374%.