基于人眼定位的快速人脸检测及归一化算法

A Rapid Approach for Face Normalization Based on Human Eyes Location

本文提出了一种基于人眼定位的有效人脸图像归一化算法。该算法首先利用Harr特征的快速检测法从图像中检测出人脸的大致位置,然后基于人脸的几何分布特征和灰度信息特征准确检测人眼瞳孔位置建立人脸坐标系,最后对人脸图像作旋转、尺度和灰度的归一化校正。实验结果证明,该算法能够有效并准确地检测和校正人脸,可以显著提高识别率。

This paper presents a new face normalization method based on eyes location. First, the face is roughly located from the original image using a rapid face detection scheme hased on a hoosted cascade of simple Haar-like features. Second, we accurately locate the pupils of eyes in the face image according to the proportional relationships of face features and gray information. Then a coordinate system is established. Finally, we normalize the rotation, scale and grayscale of the face image. The experimental results show that this algorithm can detect and normalize the face image efficiently and accurately, and it can also improve the face recognition obviously.