Compressive sensing of multispectral image based on PCA and Bregman split

We reconstruct the multispectral image based on compressive sensing theory. Both spatial domain regularization and transform domain regularization are employed in the proposed objective function. Bregman split method is used to optimize the proposed objective function. In order to making use of the correlation features between different channels of multispectral image, principal component analysis (PCA) is introduced into the shrinkage step of the spatial domain regularization. For further enhance the performance of CS reconstruction, the similarity of wavelet coefficients between different channels are also explored in the shrinkage step of transform domain. We compare the proposed method with some other methods. Experiments validate the better performances of the proposed method, and it is attributed to combine two regularizations and employ the spectral correlation between channels.