Blind separation of permuted alias image based on K-SVD dictionary learning

In this work, a new blind separation algorithm for permuted alias image based on dictionary learning is proposed according to a type of permuted alias image with noise diversity. Sparse representation of permuted alias image is obtained by dictionary learning method, since it has high adaptability and its representation result has higher sparsity degrees than that of parameter dictionary. An optimal permuted alias image is achieved by conducting sparse representation with K-SVD dictionary learning algorithm restrained with nonzero element number. The size and the location of permuting region is found by detecting the subtraction image, which is defined as the difference between the reconstructed permuted alias image and the original permuted alias image. The permuting region is optimized by implementing image morphological operation and is separated from the permuted alias image by the threshold. Experimental results show that the permuting sub-images can be efficiently separated from the permuted alias image, which is not affected by the size, location, number of permuting sub-images and noise level of the permuting sub-images. © 2015 SERSC.