Learning sparse dictionaries with a popularity-based model

Sparse signal representation based on overcomplete dictionaries has recently been extensively investigated, rendering the state-of-the-art results in signal, image and video processing. We propose a novel dictionary learning algorithm-the PK-SVD algorithm-which assumes prior probabilities on the dictionary atoms and learns a sparse dictionary under a popularity-based model. The prior distribution brings the flexibility that is desirable in applications. We examine our algorithm in both synthetic tests and image denoising experiments.