An Image Database for Design and Evaluation of Visual Quality Metrics in Synthetic Scenarios

Traditional approach to collect mean opinion score (MOS) values for evaluation of full-reference image quality metrics has two serious drawbacks. The first drawback is a nonlinearity of MOS, only partially compensated by the use of rank order correlation coefficients in a further analysis. The second drawback are limitations on number of distortion types and distortion levels in image database imposed by a maximum allowed time to carry out an experiment. One of the largest of databases used for this purpose, TID2013, has almost reached these limitations, which makes an extension of TID2013 within the boundaries of this approach to be practically unfeasible. In this paper, a novel methodology to collect MOS values, with a possibility to infinitely increase a size of a database by adding new types of distortions, is proposed. For the proposed methodology, MOS values are collected for pairs of distortions, one of them being a signal dependent Gaussian noise. A technique of effective linearization and normalization of MOS is described. Extensive experiments for linearization of MOS values to extend TID2013 database are carried out.

Download Full-text

Combined full-reference image visual quality metrics

Electronic Imaging ◽

10.2352/issn.2470-1173.2016.15.ipas-180 ◽

2016 ◽

Vol 2016 (15) ◽

pp. 1-10 ◽

Cited By ~ 3

Author(s):

Oleg I Ieremeiev ◽

Vladimir V Lukin ◽

Nikolay N Ponomarenko ◽

Karen O Egiazarian ◽

Jaakko Astola

Keyword(s):

Visual Quality ◽

Quality Metrics ◽

Reference Image ◽

Full Reference

Download Full-text

Image visual quality metrics verification by TID2013: Exploring of mean square error drawbacks

2014 5th European Workshop on Visual Information Processing (EUVIP) ◽

10.1109/euvip.2014.7018376 ◽

2014 ◽

Cited By ~ 4

Author(s):

Nikolay Ponomarenko ◽

Vladimir Lukin ◽

Oleg Ieremeiev ◽

Benoit Vozel ◽

Kacem Chehdi ◽

...

Keyword(s):

Mean Square Error ◽

Visual Quality ◽

Quality Metrics ◽

Mean Square

Download Full-text

Colourlab Image Database: Geometric Distortions

Color and Imaging Conference ◽

10.2352/issn.2169-2629.2021.29.258 ◽

2021 ◽

Vol 2021 (29) ◽

pp. 258-263

Author(s):

Marius Pedersen ◽

Seyed Ali Amirshahi

Keyword(s):

Image Quality ◽

High Performance ◽

Image Database ◽

Quality Metrics ◽

Current Image ◽

Geometric Distortions ◽

Image Quality Metrics ◽

Objective Metrics ◽

Reference Images

Over the years, a high number of different objective image quality metrics have been proposed. While some image quality metrics show a high correlation with subjective scores provided in different datasets, there still exists room for improvement. Different studies have pointed to evaluating the quality of images affected by geometrical distortions as a challenge for current image quality metrics. In this work, we introduce the Colourlab Image Database: Geometric Distortions (CID:GD) with 49 different reference images made specifically to evaluate image quality metrics. CID:GD is one of the first datasets which include three different types of geometrical distortions; seam carving, lens distortion, and image rotation. 35 state-ofthe-art image quality metrics are tested on this dataset, showing that apart from a handful of these objective metrics, most are not able to show a high performance. The dataset is available at <ext-link ext-link-type="url" xlink:href="http://www.colourlab.no/cid">www.colourlab.no/cid</ext-link>.

Download Full-text