Dictionary Learning for Image Coding Based on Multisample Sparse Representation

In this brief we propose a multisample sparse representation (MSR)-based online dictionary-learning approach to encode images more efficiently. To minimize the reconstructed error while handling a variety of image samples, we develop a multisample sparse representation method capable of obtaining sparser coefficients combined with learning dictionaries on-the-fly. With a well-learned dictionary, we further derive an MSR-based image coding approach to encode the quantized sparse coefficients with reduced reconstructed errors. Experimental results demonstrate rapid convergence of the proposed dictionary-learning algorithm and improved rate-distortion performance over other competitive image compression schemes both subjectively and quantitatively, validating the effectiveness of the proposed approach.