Blind Image Quality Assessment for Super Resolution via Optimal Feature Selection

Beron, Juan; Benítez-Restrepo, Hernán Darío; Bovik, Alan C.

doi:10.1109/access.2020.3014497

Cited by 18 publications

(4 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the spatial discontinuity of pixel intensity is closely relevant to the perception score of SR image, hence this paper applies principal component analysis (PCA) [ 17 ] to image blocks and uses corresponding singular values to describe the spatial discontinuity. In order to enrich the initial feature set, this paper also extracted the directional Log-Derivative based on MSCN coefficient used in [ 33 ]. In general, this paper extracted 10 categories of image features from different fields, including 470 features, as shown in Table 1 .…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Super Resolution Image Visual Quality Assessment Based on Feature Optimization

Shu

Huang

Yan

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Most existing no-referenced image quality assessment (NR-IQA) algorithms need to extract features first and then predict image quality. However, only a small number of features work in the model, and the rest will degrade the model performance. Consequently, an NR-IQA framework based on feature optimization is proposed to solve this problem and apply to the SR-IQA field. In this study, we designed a feature engineering method to solve this problem. Specifically, the features associate with the SR images were first collected and aggregated. Furthermore, several advanced feature selection algorithms were used to sort the feature sets according to their importance, and the importance matrix of features is obtained. Then, we examined the linear relationship between the number of features and Pearson linear correlation coefficient (PLCC) to determine the optimal number of features and the optimal feature selection algorithm, so as to obtain the optimal model. The results showed that the image quality scores predicted by the optimal model are in good agreement with the human subjective scores. Adopting the proposed feature optimization framework, we can effectively reduce the number of features in the model and obtain better performance. The experimental results indicated that SR image quality can be accurately predicted using only a small part of image features. In summary, we proposed a feature optimization framework to solve the current problem of irrelevant features in SR-IQA, and an SR image quality assessment model was proposed consequently.

show abstract

Section: Methodsmentioning

confidence: 99%

“…As mentioned in [ 33 ], one problem of feature selection is how to determine the number of features in the model. In this section, we will investigate the linear correlation between the number of features and PLCC to determine the optimal number of features for the model.…”

Section: Methodsmentioning

confidence: 99%

Super Resolution Image Visual Quality Assessment Based on Feature Optimization

Shu

Huang

Yan

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…A number of no-reference metrics are also used for video super-resolution. Most of them train regression models on statistical features extracted from upscaled frames (Ma et al, 2017;Zhang et al, 2019;Beron et al, 2020), achieving a Spearman correlation of 0.740 to 0.939 and a Pearson correlation of 0.728 to 0.9463, depending on the implementation and test dataset. Also, many no-reference metrics are based on features extracted using a pretrained neural network-VGGNet, for example (Zhang et al, 2021).…”

Section: Related Workmentioning

confidence: 99%

ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution

Kirillova¹,

Eugene²,

Antsiferova³

et al. 2021

Preprint

View full text Add to dashboard Cite

Despite the growing popularity of video super-resolution (VSR), there is still no good way to assess the quality of the restored details in upscaled frames. Some SR methods may produce the wrong digit or an entirely different face. Whether a method's results are trustworthy depends on how well it restores truthful details. Image super-resolution can use natural distributions to produce a high-resolution image that is only somewhat similar to the real one. VSR enables exploration of additional information in neighboring frames to restore details from the original scene. The ERQA metric, which we propose in this paper, aims to estimate a model's ability to restore real details using VSR. On the assumption that edges are significant for detail and character recognition, we chose edge fidelity as the foundation for this metric. Experimental validation of our work is based on the MSU Video Super-Resolution Benchmark, which includes the most difficult patterns for detail restoration and verifies the fidelity of details from the original frame. Code for the proposed metric is publicly available at https://github.com/msu-video-group/ERQA. a https://orcid.

show abstract

“…Most of the recent no-reference (NR) IQA methods for SR images usually focus on only one kind of the degradation, which limits the representation of information loss. There are different hand-crafted extractors to describe the textural features, such as the local/global frequency features [9], spatial principal component analysis (PCA) features [10], and the mean subtracted contrast normalized (MSCN) coefficients [11]. The textural features are used for evaluating the difference between the SR images and the natural images by natural scene statistics (NSS).…”

Section: Introductionmentioning

confidence: 99%

Textural-Perceptual Joint Learning for No-Reference Super-Resolution Image Quality Assessment

Liu¹,

Jia²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Image super-resolution (SR) has been widely investigated in recent years. However, it is challenging to fairly estimate the performances of various SR methods, as the lack of reliable and accurate criteria for perceptual quality. Existing SR image quality assessment (IQA) metrics usually concentrate on the specific kind of degradation without distinguishing the visual sensitive areas, which have no adaptive ability to describe the diverse SR degeneration situations. In this paper, we focus on the textural and structural degradation of image SR which acts as a critical role for visual perception, and design a dual stream network to jointly explore the textural and structural information for quality prediction, dubbed TSNet. By mimicking the human vision system (HVS) that pays more attention to the significant areas of the image, we develop the spatial attention mechanism to make the visual-sensitive areas more distinguishable, which improves the prediction accuracy. Feature normalization (F-Norm) is also developed to investigate the inherent spatial correlation of SR features and boost the network representation capacity. Experimental results show the proposed TSNet predicts the visual quality more accurate than the state-ofthe-art IQA methods, and demonstrates better consistency with the human's perspective. The source code will be made available at http://github.com/yuqing-liu-dut/NRIQA SR.

show abstract

Blind Image Quality Assessment for Super Resolution via Optimal Feature Selection

Cited by 18 publications

References 57 publications

Super Resolution Image Visual Quality Assessment Based on Feature Optimization

Super Resolution Image Visual Quality Assessment Based on Feature Optimization

ERQA: Edge-Restoration Quality Assessment for Video Super-Resolution

Textural-Perceptual Joint Learning for No-Reference Super-Resolution Image Quality Assessment

Contact Info

Product

Resources

About