Full Reference Image Quality Assessment Based on Visual Salience With Color Appearance and Gradient Similarity

Cs, Shi; Lin, Yandan

doi:10.1109/access.2020.2995420

Cited by 26 publications

(15 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This mechanism obviously affects human perceptual quality judgements. Previously published FR-IQA methods [14,[16][17][18] utilize visual saliency in the final pooling stage of the algorithm. To be more specific, visual saliency is used as weight in the weighted averaging of local image quality scores, emphasizing image regions that are more salient to the human visual system.…”

Section: Motivation and Contributionsmentioning

confidence: 99%

Saliency-Guided Local Full-Reference Image Quality Assessment

Varga

2022

Signals

View full text Add to dashboard Cite

Research and development of image quality assessment (IQA) algorithms have been in the focus of the computer vision and image processing community for decades. The intent of IQA methods is to estimate the perceptual quality of digital images correlating as high as possible with human judgements. Full-reference image quality assessment algorithms, which have full access to the distortion-free images, usually contain two phases: local image quality estimation and pooling. Previous works have utilized visual saliency in the final pooling stage. In addition to this, visual saliency was utilized as weights in the weighted averaging of local image quality scores, emphasizing image regions that are salient to human observers. In contrast to this common practice, visual saliency is applied in the computation of local image quality in this study, based on the observation that local image quality is determined both by local image degradation and visual saliency simultaneously. Experimental results on KADID-10k, TID2013, TID2008, and CSIQ have shown that the proposed method was able to improve the state-of-the-art’s performance at low computational costs.

show abstract

Section: Motivation and Contributionsmentioning

confidence: 99%

Saliency-Guided Local Full-Reference Image Quality Assessment

Varga

2022

Signals

View full text Add to dashboard Cite

show abstract

“… Structure similarity index (SSIM): SSIM is defined as follows 45–47 :

SSIM (I, \overset{truê}{I}) = \frac{1}{F} \sum_{n = 1}^{F} \{(\frac{2 μ_{xyn} {\overset{truê}{μ}}_{xyn} + C 1}{μ_{xyn} + {\overset{truê}{μ}}_{xyn} + C 2}) (\frac{2 γ_{xyn} + C 2}{σ_{xyn} + {\overset{truê}{σ}}_{xyn} + C 2})\}

where

σ_{italicxyn}

is the standard deviation of reference n th frame,

{\overset{σ}{true}}_{italicxyn}

is the standard deviation of distorted n th frame, and

γ_{italicxyn}

is the covariance between reference and distorted n th frame. C1 = 0.09 ×

255^{2}

and C2 = 0.81 ×

255^{2}

are the weights based on HVS system.…”

Section: System Designmentioning

confidence: 99%

Quality assessment for terrestrial digital video broadcast over optical wireless communication‐passive optical network under moderately turbulent regime with spatial diversity

Gill

Singh

et al. 2022

Int J Communication

View full text Add to dashboard Cite

Summary The preceding decade has seen successful rollout of 5G and convergence of broadcast broadband and telecom sector. The near future bandwidth demands for services such as advanced immersive multimedia are even more challenging. This has led to advent of 6G. The access technologies need to provide virtually unlimited data rates to support majority of applications in 6G. The optical wireless communication (OWC) with its inherent advantages is a potential enabler in this scenario. However, phenomenon such as atmospheric turbulence poses a serious degradation to performance of such systems. For multimedia services, end user perception is the ultimate quality indicator. To ascertain this quality in quantitative terms, full reference quality metrics are employed for communication purposes. In this paper, digital video broadcasting terrestrial (DVB‐T) videos with varying complexities are transmitted over OWC‐passive optical network (PON) architecture. For performance enhancement 2 × 2 repetitive coding MIMO is employed with maximal ratio combining receiver. A total of 6 video quality assessment (VQA) metrics are evaluated for the system w.r.t channel parameter as Rytov variance. For all the VQA metrics, an enhancement in the performance is observed by using MIMO technique. This performance improvement is more prominent for more complex video as compared to less complex video. As for the limiting case BER of 10−3 gives a limiting link distance of 1350 m; however with VQA metrics, the limiting case distance is 1280 m. By the use of 2 × 2 MIMO techniques, this distance enhances by 20–25 m.

show abstract

“…Our proposed algorithm was compared to several state-of-the-art FR-IQA metrics, including SSIM [12], MS-SSIM [14], MAD [46], GSM [53], HaarPSI [20], MDSI [54], CSV [55], GMSD [19], DSS [56], VSI [57], PerSIM [58], BLeSS-SR-SIM [59], BLeSS-FSIM [59], BLeSS-FSIMc [59], LCSIM1 [39], ReSIFT [60], MS-UNIQUE [61], RVSIM [62], 2stepQA [63], SUMMER [64], CEQI [65], CEQIc [65], VCGS [66], and DISTS [67], whose original source code are available online. Moreover, we reimplemented SSIM CNN [40] in MATLAB R2019a 1 .…”

Section: Comparison To the State-of-the-artmentioning

confidence: 99%

A combined full-reference image quality assessment approach based on convolutional activation maps

Varga

2020

Preprint

View full text Add to dashboard Cite

The goal of full-reference image quality assessment (FR-IQA) is to predict the quality of an image as perceived by human observers with using its pristine, reference counterpart. In this study, we explore a novel, combined approach which predicts the perceptual quality of a distorted image by compiling a feature vector from convolutional activation maps. More specifically, a reference-distorted image pair is run through a pretrained convolutional neural network and the activation maps are compared with a traditional image similarity metric. Subsequently, the resulted feature vector is mapped onto perceptual quality scores with the help of a trained support vector regressor. A detailed parameter study is also presented in which the design choices of the proposed method is reasoned. Furthermore, we study the relationship between the amount of training images and the prediction performance. Specifically, it is demonstrated that the proposed method can be trained with few amount of data to reach high prediction performance. Our best proposal -ActMapFeat -is compared to the state-of-the-art on six publicly available benchmark IQA databases, such as KADID-10k, TID2013, TID2008, MDID, CSIQ, and VCL-FER. Specifically, our method is able to significantly outperform the state-of-the-art on these benchmark databases. This paper is accompanied by the source code of the proposed method: https://github.com/Skythianos/FRIQA-ActMapFeat.

show abstract

Full Reference Image Quality Assessment Based on Visual Salience With Color Appearance and Gradient Similarity

Cited by 26 publications

References 41 publications

Saliency-Guided Local Full-Reference Image Quality Assessment

Saliency-Guided Local Full-Reference Image Quality Assessment

Quality assessment for terrestrial digital video broadcast over optical wireless communication‐passive optical network under moderately turbulent regime with spatial diversity

A combined full-reference image quality assessment approach based on convolutional activation maps

Contact Info

Product

Resources

About