A New Generalized Robust Principal Component Analysis Model and Its Application to Image Denoising
In this paper,based on the combination of the robust principal compo-nent analysis(WSNM-RPCA)model with weighted Sp norm minimization and the generalized robust principal component analysis(GRPCA)model,a new generalized robust principal component analysis(GWSLRPCA)model is reconstructed by using the l2,1 norm,which improves the accuracy of the recovery of the important rank components of the matrix,and uses the alternating direction multiplier method of random ordering to solve the new model.The numerical experiment results show that the new model GWSLRPCA can not only separate the effective low rank infor-mation of the picture and other noise parts from the picture polluted by mixed noise,but also have better image restoration effect.In terms of objective evaluation crite-ria,GWSLRPCA data are also better than Mean-Filter,WSNM-RPCA and GRPCA models.
Weighted Sp norml2,1 normmixed noiserobustnessrandom sortingalternating direction multiplier method
万方数据
