K
Karl Skretting
Researcher at University of Stavanger
Publications - 32
Citations - 1005
Karl Skretting is an academic researcher from University of Stavanger. The author has contributed to research in topics: Sparse approximation & Matching pursuit. The author has an hindex of 10, co-authored 31 publications receiving 932 citations.
Papers
More filters
Journal ArticleDOI
Recursive Least Squares Dictionary Learning Algorithm
Karl Skretting,Kjersti Engan +1 more
TL;DR: The recursive least squares dictionary learning algorithm, RLS-DLA, is presented, which can be used for learning overcomplete dictionaries for sparse signal representation and a forgetting factor can be introduced and easily implemented in the algorithm.
Journal ArticleDOI
Family of iterative LS-based dictionary learning algorithms, ILS-DLA, for sparse signal representation
TL;DR: This work presents a family of iterative least squares based dictionary learning algorithms (ILS-DLA), including algorithms for design of signal dependent block based dictionaries and overlapping dictionaries, as generalizations of transforms and filter banks, respectively.
Proceedings ArticleDOI
Image compression using learned dictionaries by RLS-DLA and compared with K-SVD
Karl Skretting,Kjersti Engan +1 more
TL;DR: The proposed compression scheme using RLS-DLA learned dictionaries in the 9/7 wavelet domain performs better than using dictionaries learned by other methods, and the compression rate is just below the JPEG-2000 rate which is promising considering the simple entropy coding used.
Journal ArticleDOI
Texture classification using sparse frame-based representations
Karl Skretting,John Hakon Husoy +1 more
TL;DR: The FTCM is applied to nine test images of natural textures commonly used in other texture classification work, yielding excellent overall performance.
Dissertation
Sparse Signal Representation using Overlapping Frames
TL;DR: This thesis solves step (2) of the general frame design problem using the compact notation of linear algebra, and proposes a new method for texture classification, denoted Frame Texture Classification Method, which may be useful in frame analysis in the future.