基于小波变换和去噪模型的光照不变人脸识别

针对正面光照人脸识别的难点，提出了一种应用小波变换和去噪模型的光照不变人脸识别算法。利用对图像的高频小波系数进行处理并运用去噪模型，提取光照人脸图像中的光照不变量，同时增强图像边缘特征，这有利于提取的光照不变量保持更多的人脸识别信息。在Yale B和CMU PIE人脸库上的实验结果表明，所提算法可以显著提高光照人脸图像的识别率。

Illumination invariant face recognition based on wavelet transform and denoising model

The recognition of frontal facial appearance with illumination is a difficult task for face recognition. In this paper, a novel illumination invariant extraction method was proposed to deal with the illumination problem based on wavelet transform and denoising model. The illumination invariant was extracted in wavelet domain by using wavelet-based denoising techniques. Through manipulating the high frequency wavelet coefficient combined with denoising model, the edge features of the illumination invariants were enhanced and more useful information was restored in illumination invariants, which could lead to an excellent face recognition performance. The experimental results on Yale face database B and CMU PIE face database show that satisfactory recognition rate can be achieved by the proposed method.