Blind image quality assessment without training on human opinion scores

Mittal, Anish; Soundararajan, Rajiv; Muralidhar, Gautam S.; Bovik, Alan C.; Ghosh, Joydeep

doi:10.1117/12.981761

Cited by 10 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies [ 35 , 36 , 37 , 38 , 39 ] have found that image distortion processes affect image anisotropy. To capture this, we calculate the variation of the non-cardinal orientation energies

[ 40 ]:

where

and

are the sample mean and standard deviation of the non-cardinal orientation energies, and

is employed to capture the degree of anisotropy of the image, and is used as a quality feature.…”

Section: Proposed Dff-iqa Methodsmentioning

confidence: 99%

No-Reference Image Quality Assessment Based on Dual-Domain Feature Fusion

Cui

2020

Entropy

View full text Add to dashboard Cite

Image quality assessment (IQA) aims to devise computational models to evaluate image quality in a perceptually consistent manner. In this paper, a novel no-reference image quality assessment model based on dual-domain feature fusion is proposed, dubbed as DFF-IQA. Firstly, in the spatial domain, several features about weighted local binary pattern, naturalness and spatial entropy are extracted, where the naturalness features are represented by fitting parameters of the generalized Gaussian distribution. Secondly, in the frequency domain, the features of spectral entropy, oriented energy distribution, and fitting parameters of asymmetrical generalized Gaussian distribution are extracted. Thirdly, the features extracted in the dual-domain are fused to form the quality-aware feature vector. Finally, quality regression process by random forest is conducted to build the relationship between image features and quality score, yielding a measure of image quality. The resulting algorithm is tested on the LIVE database and compared with competing IQA models. Experimental results on the LIVE database indicate that the proposed DFF-IQA method is more consistent with the human visual system than other competing IQA methods.

show abstract

[ 40 ]:

where

and

are the sample mean and standard deviation of the non-cardinal orientation energies, and

is employed to capture the degree of anisotropy of the image, and is used as a quality feature.…”

Section: Proposed Dff-iqa Methodsmentioning

confidence: 99%

No-Reference Image Quality Assessment Based on Dual-Domain Feature Fusion

Cui

2020

Entropy

View full text Add to dashboard Cite

show abstract

“…For NR IQA metrics, some learning-based methods [27,28,29,30,31,32,33,34,35,36,37,38,39,40,41] are proposed to simulate HVS to estimate the image quality. In training stage, they learn the relationship between image features and image quality scores using the training set (humans labeled images' quality scores).…”

Section: Image Quality Assessment (Iqa)mentioning

confidence: 99%

Fidelity-Naturalness Evaluation of Single Image Super Resolution

Xuan¹,

Zhu²,

Li³

et al. 2015

Preprint

View full text Add to dashboard Cite

We study the problem of evaluating super resolution methods. Traditional evaluation methods usually judge the quality of super resolved images based on a single measure of their difference with the original high resolution images. In this paper, we proposed to use both fidelity (the difference with original images) and naturalness (human visual perception of super resolved images) for evaluation. For fidelity evaluation, a new metric is proposed to solve the bias problem of traditional evaluation. For naturalness evaluation, we let humans label preference of super resolution results using pair-wise comparison, and test the correlation between human labeling results and image quality assessment metrics' outputs. Experimental results show that our fidelity-naturalness method is better than the traditional evaluation method for super resolution methods, which could help future research on singleimage super resolution.

show abstract

“…Liu et al [42] utilized the local spatial and spectral entropy features on distortion images. OU methods characterize image quality as the distance between the quality aware NSS feature model and the features extracted from distorted images [24] [43]. Thus, they have the advantage that they do not require training on the databases containing MOS.…”

Section: Introductionmentioning

confidence: 99%