DocumentCode
3494223
Title
Unsupervised image compression using graphcut texture synthesis
Author
Ierodiaconou, Stephen ; Byrne, James ; Bull, David R. ; Redmill, David ; Hill, Paul
Author_Institution
Dept. of Electr. & Electron. Eng., Univ. of Bristol, Bristol, UK
fYear
2009
fDate
7-10 Nov. 2009
Firstpage
2289
Lastpage
2292
Abstract
An unsupervised image compression-by-synthesis system is proposed utilising wavelet based image segmentation and analysis combined with patch based texture synthesis. High perceptual quality is ensured using an artefact detection algorithm in the encoder loop. EBCOT is used to transform code texture samples and residual image data. Resulting bitrate savings of up to approximately 17% over JPEG2000 for little change in perceptual quality have been shown.
Keywords
data compression; image coding; image segmentation; image texture; wavelet transforms; EBCOT; JPEG2000; artefact detection algorithm; graphcut texture synthesis; patch based texture synthesis; unsupervised image compression; wavelet based image segmentation; Bit rate; Codecs; Decoding; Image analysis; Image coding; Image segmentation; Image texture analysis; Performance analysis; Signal synthesis; Transform coding; Image; compression; segmentation; synthesis; texture;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location
Cairo
ISSN
1522-4880
Print_ISBN
978-1-4244-5653-6
Electronic_ISBN
1522-4880
Type
conf
DOI
10.1109/ICIP.2009.5414425
Filename
5414425
Link To Document