Unsupervised image compression-by-synthesis within a JPEG framework

JD Byrne, SP Ierodiaconou, DR Bull, DW Redmill, PR Hill

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

15 Citations (Scopus)


An image compression scheme is proposed, utilising wavelet- based image segmentation and texture analysis, and patch- based texture synthesis. This has been incorporated into a JPEG framework. Homogeneous textured regions are identified and removed prior to transform coding. These regions are then replaced at the decoder by synthesis from marked samples, and colour matched to ensure similarity to the original. Experimental results on natural images show bitrate savings of over 18% compared with JPEG for little change in measured visual quality.
Translated title of the contributionUnsupervised image compression-by-synthesis within a JPEG framework
Original languageEnglish
Title of host publication15th IEEE International Conference on Image Processing (ICIP 2008), San Diego, USA
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages2892 - 2895
Number of pages4
ISBN (Print)9781424417650
Publication statusPublished - 12 Oct 2009

Fingerprint Dive into the research topics of 'Unsupervised image compression-by-synthesis within a JPEG framework'. Together they form a unique fingerprint.

Cite this