Abstract | ||
---|---|---|
Recently, there has been a trend of investigating weighting/pooling strategies in the research of image quality assessment (IQA). The saliency maps, information content maps and other weighting strategies were reportedly to be able to amend performance of IQA metrics to a sizable margin. In this work, we will show that local structural similarity is itself an effective yet simple weighting scheme leading to substantial performance improvement of IQA. More specifically, we propose a Structural similarity Weighted SSIM (SW-SSIM) metric by locally weighting the SSIM map with local structural similarities computed using SSIM itself. Experimental results on LIVE database confirm the performance of SW-SSIM as compared to some major weighting/pooling type of IQA methods, such as MS-SSIM, WSSIM and IW-SSIM. We would like to emphasize that our SW-SSIM is merely a straightforward realization of a more general framework of locally weighting IQA metric using itself as similarity measures. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICMEW.2013.6618416 | ICME Workshops |
Keywords | Field | DocType |
live database,structural similarity weighting,image quality assessment (iqa),image matching,information content maps,iw-ssim,ms-ssim,wssim,sw-ssim,locally weighting iqa metric,pooling,weighting-pooling strategies,structural similarity weighted ssim metric,image quality assessment,saliency,structural similarity,saliency maps,visualization,databases,correlation,image quality,psnr,measurement,transform coding | Computer vision,Weighting,Pattern recognition,Image matching,Computer science,Salience (neuroscience),Pooling,Image quality,Structural similarity,Artificial intelligence,Performance improvement | Conference |
Volume | Issue | ISSN |
null | null | 2330-7927 |
Citations | PageRank | References |
14 | 0.68 | 10 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ke Gu | 1 | 1321 | 77.21 |
Guangtao Zhai | 2 | 1707 | 145.33 |
Xiaokang Yang | 3 | 3581 | 238.09 |
Wenjun Zhang | 4 | 1789 | 177.28 |
Min Liu | 5 | 335 | 40.49 |