TY - GEN A1 - Köhler, Alexander A1 - Breuß, Michael A1 - Shabani, Shima ED - Frolkovič, P. ED - Mikula, K. ED - Ševčovič, D. T1 - Dictionary learning with the K-SVD algorithm for recovery of highly textured images : an experimental analysis T2 - Proceedings of the Conference Algoritmy 2024 N2 - Image recovery by dictionary learning is of potential interest for many possible applications. To learn a dictionary, one needs to solve a minimization problem where the solution should be sparse. The K-SVD formalism, which is a generalization of the K-means algorithm, is one of the most popular methods to achieve this aim. We explain the preprocessing that is needed to bring images into a manageable format for the optimization problem. The learning process then takes place in terms of solving for sparse representations of the image batches. The main contribution of this paper is to give an experimental analysis of the recovery for highly textured imagery. For our study, we employ a subset of the Brodatz database. We show that the recovery of sharp edges plays a considerable role. Additionally, we study the effects of varying the number dictionary elements for that purpose. KW - Image recovery KW - Dictionary learning KW - Sparse representation KW - Textured images Y1 - 2024 UR - http://www.iam.fmph.uniba.sk/amuc/ojs/index.php/algoritmy/article/view/2199 SN - 978-80-89829-33-0 SP - 264 EP - 273 PB - Jednota slovenských matematikov a fyzikov CY - Bratislava ER - TY - GEN A1 - Köhler, Alexander A1 - Breuß, Michael A1 - Shabani, Shima T1 - Dictionary Learning with the K-SVDAlgorithm for Recovery of Highly Textured Images T2 - Preprints.org N2 - Image recovery by dictionary learning is of potential interest for many possible applications. To learn a dictionary, one needs to solve a minimization problem where the solution should be sparse. The K-SVD formalism, which is a generalization of the K-means algorithm, is one of the most popular methods to achieve this aim. We explain the preprocessing that is needed to bring images into a manageable format for the optimization problem.The learning process then takes place in terms of solving for sparse representations of the image batches. The main contribution of this paper is to give an experimental analysis of the recovery for highly textured imagery. For our study, we employ a subset of the Brodatz database. We show that the recovery of sharp edges plays a considerable role. Additionally, we study the effects of varying the number dictionary elements for that purpose. Y1 - 2024 U6 - https://doi.org/10.20944/preprints202406.0355.v1 PB - MDPI AG ER -