基于DDR的字典学习在光照变化人脸识别中的应用

针对光照变化人脸识别中大多数现有的人脸识别算法只能单独实施降维或者字典学习而不能完全利用训练样本判别信息的问题，提出了基于判别性降维的字典学习算法。首先，利用经典的特征提取算法PCA初始化降维投影矩阵；然后，计算字典和系数，通过联合降维与字典学习使得投影矩阵和字典更好地相互拟合；最后，利用迭代算法输出字典和投影矩阵，并利用经l2-范数正则化的分类器完成人脸的识别。在PIE及扩展的YaleB两大人脸数据库上得到了验证了所提算法的有效性及可靠性，实验结果表明，相比几种较为先进的线性表示算法，所提算法在处理光照变化人脸识别时取得了更高的识别率。

Application of Dictionary Learning Based on DDR in Face Recognition with Illustration Variation

Most existing face recognition algorithms can not use discriminative information of samples due to they only carry out dimensionality reduction or dictionary learning, for which dictionary learning algorithm based on discriminative dimensionality reduction is proposed. Firstly, typical feature extraction algorithm PCA is used to initialize dimensionality reduction projection matrix. Then, dictionary and coefficient is computed and the dictionary can match with each other by jointing dimension reduction and dictionary learning. Finally, dictionary and projection matrix is outputted by using iterative algorithm, and classifier regularized by l2-norm is used to finish face recognition. The effectiveness and reliability of proposed algorithm has been verified by experiments on PIE and extended YaleB face databases. Experimental results show that proposed algorithm has higher recognition accuracy than several other advanced linear represent algorithms in dealing with face recognition with illustration variation.