基于LBP算子与EMD的人脸识别算法

An Algorithm of Face Recognition Based on LBP Operator and EMD

提出了基于LBP算子与EMD的人脸识别算法.该方法先通过图像预处理,把光照变化控制在一定范围内,然后提取图像的局部LBP特征,获得图像的LBP直方图.EMD可以准确地计算直方图的距离,因此本文采用EMD方法对LBP直方图进行计算,完成对图像相似性的度量.在GTAV人脸库上的实验结果表明,本文算法对光照变化和噪声更加鲁棒,EMD测度方法比χ2测度方法具有更高的识别率.

This paper proposes an algorithm of face recognition based on LBP operator and EMD. It uses a simple and efficient image preprocessing to limit the illumination variation. And then the LBP histogram of the image is obtained by extracting the local LBP feature. The EMD can accurately calculate the distance of the histogram, and thus the use of EMD can examine of image similarity by calculating the LBP histogram. In GTAV face database, the experimental results show that the algorithm is more robust to illumination changes and noise, and the EMD has a higher recognition rate than the X2 measure.