Exact Sparse Orthogonal Dictionary Learning
This addresses the issue of high mutual incoherence and lack of strict sparsity in existing dictionary learning methods for researchers in image processing and compressed sensing, representing an incremental improvement.
The paper tackles the problem of dictionary learning for sparse modeling in image processing and compressed sensing by proposing an orthogonal dictionary learning model that ensures strictly sparse codes and orthogonal dictionaries with global convergence guarantees, resulting in better denoising performance and higher computational efficiency compared to over-complete methods like K-SVD.
Over the past decade, learning a dictionary from input images for sparse modeling has been one of the topics which receive most research attention in image processing and compressed sensing. Most existing dictionary learning methods consider an over-complete dictionary, such as the K-SVD method, which may result in high mutual incoherence and therefore has a negative impact in recognition. On the other side, the sparse codes are usually optimized by adding the $\ell_0$ or $\ell_1$-norm penalty, but with no strict sparsity guarantee. In this paper, we propose an orthogonal dictionary learning model which can obtain strictly sparse codes and orthogonal dictionary with global sequence convergence guarantee. We find that our method can result in better denoising results than over-complete dictionary based learning methods, and has the additional advantage of high computation efficiency.