Blind Image Quality Assessment Based on Rank-Order Regularized Regression

Wu, Qingbo; Li, Hongliang; Wang, Zhou; Meng, Fanman; Luo, Bing; Li, Wei; Ngan, King Ngi

doi:10.1109/tmm.2017.2700206

Cited by 53 publications

(15 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It would be also better to mention that the results of subjective image quality evaluation are often used for developing objective image quality metrics. Most existing objective quality metrics are trained by nonlinear regression or rank learning [36]- [38]. They use either one of absolute or relative quality scores obtained by subjective tests.…”

Section: Discussionmentioning

confidence: 99%

Subjective Assessment of 360° Image Projection Formats

et al. 2020

View full text Add to dashboard Cite

Recently, the use of virtual reality has been spreading rapidly in many industrial fields, such as games and entertainment, and 360 • contents are widely used in various applications of the virtual reality (VR) market. The 360 • contents create a virtual space comparable to real scenes. Coupled with the rapid growth of the 360 • image/video field, many projection formats have been developed and published. However, the studies which identify the best format for a variety of applications are still limited. Therefore, it is desirable to evaluate the visual quality of the projection formats used in the current market, and the result of the evaluation can be used as an important consideration capable of providing 360 • VR service of better quality. Here, we propose a methodology for the subjective test and briefly present ten 360 • projection formats used in our experiment. The proposed methodology for the subjective test uses a combination of the Degradation Category Rating (DCR) and Pair Comparison methods. We performed the subjective test with 15 participants for each test step, the experimental setup for which followed the proposed methodology. The results show that the equirectangular projection format (best known and widely used format in most commercial products) did not give the highest quality. Hybrid equiangular cubemap and equatorial cylindrical projection gave the best quality compared with the other eight formats. Based on the results of the DCR, it is noted that different monitors (size and resolution) do not affect the ranking of 360 • image projection formats. Our work presents the ranking of ten published projection formats which is useful for identifying the best format for a future 360 • image standard. INDEX TERMS 360 • projection format, subjective evaluation, degradation category rating, pair comparison, 360 • image.

show abstract

Section: Discussionmentioning

confidence: 99%

Subjective Assessment of 360° Image Projection Formats

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Following the recommendation of ITU-T P.910 [26], we employ the simultaneous presentation method to evaluate 2 http://ivipc.uestc.edu.cn/ [61, 80] Clearly remove the rain, but destroy partial image structure 3 [41,60] Does not remove the rain, but preserve image structure 2 [21,40] Does not remove the rain, and slightly destroy image structure 1 [1,20] Does not remove the rain, and severely destroy image structure the de-raining performance. The reference image (i.e., rain image) and its associated de-rained version are simultaneously presented to the subject via a customized dialogue window.…”

Section: B Subjective Testing Methodsmentioning

confidence: 99%

“…By contrast, the dictionary learning based method, such as, Kang12 [10], clearly over smoothes the original image structure, whose MOS is only 37.63. When we change the Ding16 [6] Kang12 [9] Luo15 [10] Li16 [11] Deng17 [20] Fu17 [13] rain image to the second row, it is seen that Fu17 [14] almost does nothing for the dot-like raindrops, whose MOS drops to 40.95. While, Kang12 [10] could perfectly remove these small raindrops without obvious damage to the contour of the player, whose MOS rises to 99.68.…”

Section: Ding16mentioning

confidence: 99%

Subjective and Objective De-Raining Quality Assessment Towards Authentic Rain Image

Wang

Ngan

et al. 2020

IEEE Trans. Circuits Syst. Video Technol.

Self Cite

View full text Add to dashboard Cite

Images acquired by outdoor vision systems easily suffer poor visibility and annoying interference due to the rainy weather, which brings great challenge for accurately understanding and describing the visual contents. Recent researches have devoted great efforts on the task of rain removal for improving the image visibility. However, there is very few exploration about the quality assessment of de-rained image, even it is crucial for accurately measuring the performance of various de-raining algorithms. In this paper, we first create a deraining quality assessment (DQA) database that collects 206 authentic rain images and their de-rained versions produced by 6 representative single image rain removal algorithms. Then, a subjective study is conducted on our DQA database, which collects the subject-rated scores of all de-rained images. To quantitatively measure the quality of de-rained image with nonuniform artifacts, we propose a bi-directional feature embedding network (B-FEN) which integrates the features of global perception and local difference together. Experiments confirm that the proposed method significantly outperforms many existing universal blind image quality assessment models. To help the research towards perceptually preferred de-raining algorithm, we will publicly release our DQA database and B-FEN source code on https://github.com/wqb-uestc.Index Terms-Single image de-raining, authentic rain image, de-raining quality assessment.

show abstract

“…With the boom of perceptually friendly image/video processing systems [5]- [7], recent decades have witnessed the growing interests in the development of IQA algorithms. A large number of subject rated databases (such as, LIVE II [8], TID2013 [9], CSIQ [10], ChallengeDB [11]) and objective metrics (including the full-reference [12], reduced-reference [13], and no-reference models [14], [15]) are successively proposed to interpret the human perception of image quality from different perspectives. Thanks to the efforts of these researches, many exciting findings and technologies are verified efficient in modeling the perceptual image quality, such as, the perceptual visibility threshold [16], [17], the visual attention psychology [18], [19], the structural similarity measurement [20]- [22], the natural scene statistics [23], [24], the semantic obviousness [25], and so on.…”

Section: Introductionmentioning

confidence: 99%

A Perceptually Weighted Rank Correlation Indicator for Objective Image Quality Assessment

Meng

et al. 2018

IEEE Trans. on Image Process.

Self Cite

View full text Add to dashboard Cite

In the field of objective image quality assessment (IQA), Spearman's ρ and Kendall's τ, which straightforwardly assign uniform weights to all quality levels and assume that each pair of images is sortable, are the two most popular rank correlation indicators. These indicators can successfully measure the average accuracy of an IQA metric for ranking multiple processed images. However, two important perceptual properties are ignored. First, the sorting accuracy (SA) of high-quality images is usually more important than that of poor-quality images in many real-world applications, where only top-ranked images are pushed to the users. Second, due to the subjective uncertainty in making judgments, two perceptually similar images are usually barely sortable, and their ranks do not contribute to the evaluation of an IQA metric. To more accurately compare different IQA algorithms, in this paper, we explore a perceptually weighted rank correlation indicator, which rewards the capability of correctly ranking high-quality images and suppresses the attention towards insensitive rank mistakes. Specifically, we focus on activating a 'valid' pairwise comparison of images whose quality difference exceeds a given sensory threshold (ST). Meanwhile, each image pair is assigned a unique weight that is determined by both the quality level and rank deviation. By modifying the perception threshold, we can illustrate the sorting accuracy with a sophisticated SA-ST curve rather than a single rank correlation coefficient. The proposed indicator offers new insight into interpreting visual perception behavior. Furthermore, the applicability of our indicator is validated for recommending robust IQA metrics for both degraded and enhanced image data.

show abstract

Blind Image Quality Assessment Based on Rank-Order Regularized Regression

Cited by 53 publications

References 48 publications

Subjective Assessment of 360° Image Projection Formats

Subjective Assessment of 360° Image Projection Formats

Subjective and Objective De-Raining Quality Assessment Towards Authentic Rain Image

A Perceptually Weighted Rank Correlation Indicator for Objective Image Quality Assessment

Contact Info

Product

Resources

About