Image compression using learned dictionaries by RLS-DLA and compared with K-SVD

The recently presented recursive least squares dictionary learning algorithm (RLS-DLA) is tested in a general image compression application. Dictionaries are learned in the pixel domain and in the 9/7 wavelet domain, and then tested in a straightforward compression scheme. Results are compared with state-of-the-art compression methods. The proposed compression scheme using RLSDLA learned dictionaries in the 9/7 wavelet domain performs better than using dictionaries learned by other methods. The compression rate is just below the JPEG2000 rate which is promising considering the simple entropy coding used.

• Type: Journal
• Year: 2011
• Where: ICASSP
• Authors: Karl Skretting, Kjersti Engan
• Keywords: Compression Scheme, ICASSP 2011, Signal Processing, Straightforward Compression Scheme, Wavelet Domain