Title :
Assessing MDL in wavelet denoising and compression
Author :
Hansen, Mark ; Yu, Bin
Author_Institution :
AT&T Bell Labs., Murray Hill, NJ, USA
Abstract :
In the context of wavelet denoising and compression, we study two mixture forms of MDL model selection criteria. We find that gMDL outperforms other techniques for 1-dim curve estimation and MDL does the same for natural images. While achieving similar (if not better) MSEs, they keep much fewer coefficients. Hence they are excellent simultaneous denoisers and compressors
Keywords :
data compression; image coding; mean square error methods; noise; transform coding; wavelet transforms; 1-dim curve estimation; MDL model selection criteria; MSE; compression; gMDL; mixture forms; natural images; wavelet denoising; Compressors; Context modeling; Design optimization; Image coding; Noise reduction; Quantization; Signal denoising; Signal processing; Testing; Wavelet coefficients;
Conference_Titel :
Information Theory and Networking Workshop, 1999
Conference_Location :
Metsovo
Print_ISBN :
0-7803-5954-2
DOI :
10.1109/ITNW.1999.814344
