Sparse coding theory demonstrates that the neurons in primary visual cortex form a sparse representation of natural scenes in the viewpoint of statistics. In this paper, we propose a novel sparse coding model based on structural similarity for natural image patch feature extraction. The advantage for our model is to be able to preserve structural information from a scene, which human visual per...

-Whether sparseness can be effectively controlled is one of the key elements to measure the merits of the sparse coding algorithm. One-norm is primarily used in the sparse coding algorithm to control its sparseness currently, as well as by sparse approximation to control the sparseness of sparse coding model, but all these methods have led to slow convergence and low efficiency ultimately. In o...

A large number of image super resolution algorithms based on the sparse coding are proposed, and some algorithms realize the multi-frame super resolution. In multi-frame super resolution based on the sparse coding, both accurate image registration and sparse coding are required. Previous study on multi-frame super resolution based on sparse coding firstly apply block matching for image registra...

In this paper, we propose a novel multilayer sparse coding network capable of efficiently adapting its own regularization parameters to a given dataset. The network is trained end-to-end with a supervised task-driven learning algorithm via error backpropagation. During training, the network learns both the dictionaries and the regularization parameters of each sparse coding layer so that the re...