中文摘要：

为了减少光照变化对人脸识别算法的影响，提出了一种基于非下采样Contourlet变换（NSCT，nonsubsampled contourlet transform）的光照不变特征提取方法。人脸图像经过对数变换（LT）后，利用NSCT进行分解，得到图像的低频子带和高频方向子带；根据高频子带中NSCT系数的概率分布，给出各子带的自适应阈值，并采用折衷阈值函数进行滤波；对滤波后的子带进行NSCT逆变换，得到人脸图像的光照不变特征。在Extended YaleB和cMUPIE人脸数据库上的实验结果表明，本文方法能有效减少光照影响，显著提高了识别率。

英文摘要：

In order to alleviate the influence of illumination variations on face recognition,a novel method is proposed for extracting illumination invariant from face images. In this work,the logarithm of an original face image is first decomposed by using nonsubsampled contourlet transform （NSCT）, which is a fully shift-invafiant,multi-scale and multi-direction transform. Then each high-pa~s sub-band in NSCT domain is filtered by adaptive thresholds designed according to the probability distribution of the coeffi- cients in the sub-band. Finally, the illumination invariant is obtained by using reverse NSCT. Experimental results on the extended Yale B and the CMU PIE face data sets show that the proposed method achieves satisfactory recognition rates under varying illumination conditions.