改进型稀疏表示的图像分类方法

Images classification method based on improved sparse representation

在图像分类问题中,传统的稀疏表示算法只考虑样本整体信息,忽略样本局部结构信息;此外,稀疏表示算法要求测试样本与训练样本的人脸图像要一致对齐,当姿势与角度发生变化时分类效果明显下降.针对这些问题,提出了一种改进L2正则化稀疏表示算法.首先,通过求解最小二乘法得到稀疏系数矩阵;然后,计算样本重构残差,用稀疏度量公式量化样本之间的稀疏性;最后,在保持样本稀疏性的同时增加了样本类与类之间的局部判别信息,进而提高样本的分类性能.为了验证算法的有效性,在ORL、FERET和FEI人脸数据库与Stanford 40 Actions数据库和Caltech-UCSD Birds (CUB200-2011)数据库上进行实验.实验结果表明,该方法在不同的人脸数据库和扩展视觉数据集上取得的分类结果均优于传统稀疏表示算法及其他常用分类算法.

In the problem of image classification, the traditional sparse representation algorithms only consid- er the whole information of the sample, neglect the local structure information. Besides, those sparse representation algorithms require uniform alignment of the testing face samples and the training face samples, when the posture and angle change,the classification effect decreases obviously.Aimed at these problems, an improved L2 regulari- zation sparse representation algorithm is proposed in this paper.Firstly, the sparse coefficient matrix is obtained by solving the least square method.Then, the residuals of the reconstructed samples are calculated and the sparsity between samples is quantified by the sparse metric formula.Finally, while keeping the sparsity of samples, the lo- cal discriminant information between sample classes and classes is increased, to improve the classification per- formance of samples.To verify the effectiveness of the proposed method,many experiments are conducted on hu- man face datasets ORL, FERET, FEI and visual datasets Stanford 40 Actions and Cahech-UCSD Birds （ CUB200 -2011 ）.The experimental results show that the proposed method is superior to the traditional sparse representa- tion algorithm and other common classification algorithms on different face databases and extended visual datasets.