Open Access Open Access  Restricted Access Subscription or Fee Access

Image Decode Optimization Based on Compressive Sensing

Xue Xiao, Shen Yi-ge, Zheng Yang-bing

Abstract


The mainstream JPEG image code standard based on transforming code has been widely applied recently, while the newly emerged Compressive Sensing (CS) theory indicates the original signal can be accurately recovered at very high probability if the sparse signal gains a few or even corrupted measurements. So a JPEG decode optimization scheme based on CS is proposed to improve the quality of decoded image, which transforms the decode reconstruct process into a CS optimization recovery problem without changing the current JPEG encoder and the structure of code stream. Also a CS decode optimization scheme based on block combination is proposed to further improve the decoded image quality. Extensive experimental results demonstrate the schemes above improves the JPEG decoded image quality dramatically and the new schemes can achieve as high as 0.71db and averagely 0.51db decoding gain, and obtain a better subjective quality of reconstruction in the edge of the image area compared with the JPEG decoder based on inverse DCT.

Keywords


compressive sensing, decode optimization, total variation.

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.