Cosparse dictionary learning for the orthogonal case

Dictionary learning is usually approached by looking at the support of the sparse representations. Recent years have shown results in dictionary improvement by investigating the cosupport via the analysis-based cosparse model. In this paper we present a new cosparse learning algorithm for orthogonal dictionary blocks that provides significant dictionary recovery improvements and representation error shrinkage. Furthermore, we show the beneficial effects of using this algorithm inside existing methods based on building the dictionary as a structured union of orthonormal bases.