为了消除光照变化对人脸识别的影响,提出一种基于Gabor相位特征的光照不变量提取算法。该算法首先对图像进行光照归一化,一定程度上减弱了不同光照条件的影响;然后利用一组不同方向的2维实Gabor小波对图像进行变换,在兼顾频谱与相位信息的情况下组合变换后的Gabor系数,提取其相位特征,得到光照不变量。在Yale B 和CMU PIE 人脸库上的实验结果表明,该算法能够有效消除光照变化对人脸识别的影响,提取的光照不变量具有一定的鲁棒性。

In order to eliminate the effect of varying illumination on face recognition,a novel illumination invariant method based on the Gabor phase-frequency feature is proposed.The method first performs illumination normalization on image under various lighting conditions,which can reduce the effect of varying illumination to some extent.Secondly,a set of 2D real Gabor wavelets with different directions are used for image transformation,and multiple Gabor coefficients are combined into one whole in considering spectrum and phase.Lastly,the illumination invariant is obtained by extracting the phase feature from the combined coefficients.Experimental results on the Yale face database B and on the CMU PIE database show that the proposed method can effectively eliminate the effect of varying illumination on face recognition,and that extracted illumination invariant is robust.