Papers › FSIM: A Feature Similarity Index for Image Quality Assessment

FSIM: A Feature Similarity Index for Image Quality Assessment

31 Jan 2011IEEE Transactions on Image Processing 2011 1archive 2025-07-28

Lin Zhang, Lei Zhang, Xuanqin Mou, David Zhang

Image quality assessment (IQA) aims to use computational models to measure the image quality consistently with subjective evaluations. The well-known structural similarity index brings IQA from pixel- to structure-based stage. In this paper, a novel feature similarity (FSIM) index for full reference IQA is proposed based on the fact that human visual system (HVS) understands an image mainly according to its low-level features. Specifically, the phase congruency (PC), which is a dimensionless measure of the significance of a local structure, is used as the primary feature in FSIM. Considering that PC is contrast invariant while the contrast information does affect HVS' perception of image quality, the image gradient magnitude (GM) is employed as the secondary feature in FSIM. PC and GM play complementary roles in characterizing the image local quality. After obtaining the local quality map, we use PC again as a weighting function to derive a single quality score. Extensive experiments performed on six benchmark IQA databases demonstrate that FSIM can achieve much higher consistency with the subjective evaluations than state-of-the-art IQA metrics.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Full reference image quality assessmentImage Quality AssessmentVideo Quality Assessment

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Full reference image quality assessment DRIQ FSIMc PLCC 0.7989 #6 of 10 Archive leaderboard report
Full reference image quality assessment DRIQ FSIMc SRCC 0.7751 #6 of 10 Archive leaderboard report
Full reference image quality assessment ESPL FSIMc PLCC 0.8738 #3 of 11 Archive leaderboard report
Full reference image quality assessment ESPL FSIMc SRCC 0.8766 #3 of 11 Archive leaderboard report
Full reference image quality assessment KADID10K FSIMc SRCC 0.8537 #5 of 11 Archive leaderboard report
Full reference image quality assessment KADID10K FSIM SRCC 0.8294 #8 of 11 Archive leaderboard report
Full reference image quality assessment TID2008 FSIMc PLCC 0.8762 #7 of 13 Archive leaderboard report
Full reference image quality assessment TID2008 FSIMc SRCC 0.8840 #7 of 13 Archive leaderboard report
Image Quality Assessment MSU FR VQA Database FSIM SRCC 0.9000 #2 of 6 Archive leaderboard report
Video Quality Assessment MSU FR VQA Database FSIM KLCC 0.7418 #10 of 20 Archive leaderboard report
Video Quality Assessment MSU FR VQA Database FSIM SRCC 0.9000 #10 of 20 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset FSIM KLCC 0.26942 #43 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset FSIM PLCC 0.35083 #43 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset FSIM SROCC 0.34996 #43 of 60 Archive leaderboard report
Video Quality Assessment MSU SR-QA Dataset FSIM Type FR #43 of 60 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections