基于快速稀疏低秩和鲁棒主成分分析的图像处理算法

实际的稀疏低秩处理图像过程中，在视觉显示效果没有很大的差异的情况下，CPU的处理时间是唯一一个的评价指标。我们发现快速交替极小化(FAST PCP)和鲁棒主成分分析(RPCA)的结合是最快速、最有效的利用CPU的高效稀疏低秩处理图像的方法，并且在无法保证计算机配置的情况下，其运算速度也是最快的。在课题中，将Steffensen迭代法用于改进FAST PCP，由此得到的结果较普通版本的FAST PCP和RPCA更加好。 

Image Processing Algorithm Based on Fast Sparse Low Rank and Robust PCA

The time complexity of the algorithm is the only evaluation index in the case that the visual display effect is not very different in the actual sparse low rank processing image process.we find that the combination of fast alternating minimization(FAST PCP) and robust principal component analysis(RPCA) is a relatively fast and efficient way to use the highly efficient sparse low-rank image of the CPU,and the speed of operation is also the fastest when the computer configuration cannot be guaranteed.In this paper,the Steffensen iterative method is used to improve the FAST PCP,and the result is a more common version of FAST PCP and RPCA are better.