Objective estimation of subjective image quality assessment using multi‐parameter prediction. Issue 13 (17th October 2019)

• Record Type: Journal Article
• Authors: Maksimović‐Moićević, Sanja; Lukač, Željko; Temerinac, Miodrag
• Is Part Of: IET image processing. Volume 13:Issue 13(2019)
• Page Start: 2428
• Page End: 2435
• Publication Date: 2019-10-17
• Subjects: feature extraction -- image fusion -- image coding -- image processing -- data compression -- mean square error methods -- visual databases -- distortion; subjective image quality assessment -- multiparameter prediction -- image processing applications -- objective measurable artefacts -- objective image quality assessment -- known subjective image quality measure -- multiscale structural similarity image measure -- feature similarity image measure -- video quality measure -- two‐dimensional image quality metrics -- test image database -- available subjective image quality measures -- image content indicator; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.6143
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Objective evaluation of a subjective image quality assessment plays a significant role in the various image processing applications, such as compression, interpolation and noise reduction. The subjective image quality assessment does not only depend on some objective measurable artefacts, but also on image content and kind of distortions. Thus, a multi‐parameter prediction of the objective image quality assessment is proposed in this study. The prediction parameters are found minimising the mean square error related to the known subjective image quality measure (DMOS). This approach includes mostly used image quality metrics (peak signal‐to‐noise ratio, multi‐scale structural similarity image measure, feature similarity image measure, video quality measure) and two‐dimensional image quality metrics (2D IQM). The proposed multi‐parameter prediction has been verified on the test image database (LIVE) for compression, noise and blur distortions with available subjective image quality measures (DMOS). More reliable estimations are obtained using multi‐parameter prediction instead of only one measure. The best results are reached when an image content indicator is combined with the 2D IQM measure separately for different kinds of distortions.