Color Image Database HTID for Verification of No-Reference Metrics: Peculiarities and Preliminary Results

Ponomarenko, Nikolay N.; Bahnemiri, Sheyda Ghanbaralizadeh; Егиазарян, Карен; Єремеєв, Олег; Peltoketo, Veli-Tapani; Hakala, Jussi

doi:10.1109/euvip50544.2021.9484005

Cited by 25 publications

(29 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The compression problem is highly related with the efficient coding hypothesis proposed by Barlow as a goal for the human visual system. Note that a widely accepted perceptual distance like SSIM has a substantially lower Spearman correlation with psychophysical MOS in the same experiment (ρpSSIM, M OSq " 0.63 [33] while maxpρpD in , M OSqq " 0.77). Finally, it is important to stress a precaution when using a perceptual distance in an empirical risk minimization framework: its connection with data statistics implies a double counting effect of the probability distribution.…”

Section: Final Remarksmentioning

confidence: 69%

“…Experiment. The TID 2013 dataset [33] contains 25 reference images, x 1 , and 3000 distorted images, x 2 , with 24 types and 5 levels of severity of distortion. Also provided is the mean opinion score (MOS) for each distorted image.…”

Section: On the Relation Between Distances Induced By Autoencoders An...mentioning

confidence: 99%

“…Fig. 4 reports the Spearman correlations between the induced distance and MOS, ρpD, MOSq, for the TID 2013 database [33]. As a reference we include the correlation between the MOS and RMSE " ||x 1 ´x2 || 2 .…”

Section: On the Relation Between Distances Induced By Autoencoders An...mentioning

confidence: 99%

See 2 more Smart Citations

On the relation between statistical learning and perceptual distances

Hepburn¹,

Laparra²,

Santos-Rodríguez³

et al. 2021

Preprint

View full text Add to dashboard Cite

It has been demonstrated many times that the behavior of the human visual system is connected to the statistics of natural images. Since machine learning relies on the statistics of training data as well, the above connection has interesting implications when using perceptual distances (which mimic the behavior of the human visual system) as a loss function. In this paper, we aim to unravel the non-trivial relationship between the probability distribution of the data, perceptual distances, and unsupervised machine learning. To this end, we show that perceptual sensitivity is correlated with the probability of an image in its close neighborhood. We also explore the relation between distances induced by autoencoders and the probability distribution of the data used for training them, as well as how these induced distances are correlated with human perception. Finally, we discuss why perceptual distances might not lead to noticeable gains in performance over standard Euclidean distances in common image processing tasks except when data is scarce and the perceptual distance provides regularization.

show abstract

Section: Final Remarksmentioning

confidence: 69%

Section: On the Relation Between Distances Induced By Autoencoders An...mentioning

confidence: 99%

See 1 more Smart Citation

On the relation between statistical learning and perceptual distances

Hepburn¹,

Laparra²,

Santos-Rodríguez³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…We validate the performance of the proposed model on six public databases including LIVE [46], TID2013 [47], CSIQ, LIVEC, KonIQ-10K [48], and KADID-10k [49]. And each image has a corresponding subjective mean opinion score (MOS) or difference of mean opinion score (DMOS).…”

Section: Databasesmentioning

confidence: 99%

No‐reference image quality assessment based on multiscale feature representation

Qiao

Zhao

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

The no-reference image quality assessment (NR-IQA) method can evaluate the distortions in an image without the reference image. However, due to the diversity of the image contents and distortion types, it is hard for the existing NR-IQA algorithms to obtain competitive performance on both synthetically and authentically distorted images. To address the problem, a multiscale feature representation-based NR-IQA method that performs well for both synthetic and authentic distortions is proposed. This model consists of two parts: The feature extraction part and the feature fusion part. First, part of the Res2Net-50 network is chosen as the feature extraction part due to its high ability in increasing the range of receptive fields. Then, the feature fusion part consisting of a novel residual block and two fully connected layers is designed to fuse the extracted features and realize the quality score mapping. After a series of stepwise optimization experiments, the most competitive network architecture consisting of the feature extraction part and the feature fusion part is obtained. Comprehensive experiments on the LIVE, TID2013, CSIQ, KADID-10k, KonIQ-10K, and LIVE challenge databases demonstrate that the proposed method can work powerfully on both the synthetic and authentic distortions and also has a strong generalization ability.This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

show abstract

“…To research and develop IQA algorithms, multiple IQA image databases are established, such as LIVE [22], TID2008 [23], TID2013 [24], and CSIQ [25]. The number of images per degradation category in each database is shown in Table 1.…”

Section: Introductionmentioning

confidence: 99%

MP2020: Visual quality assessment database for macro photography images

Sang

Cao

Liu³

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

With the development of mobile phone camera technology, mobile phones can take a large number of macro photography images that previously could only be taken by professional cameras. Therefore, it is of great significance to study the quality of macro photography images. For this reason, a macro photography image visual quality evaluation database is established and it is named as MP2020. The database contains 100 reference images and 800 distorted images of four distortion types, including 200 distorted images of JPEG 2000, 200 distorted images of JPEG, 200 distorted images of white noise, and 200 distorted images of Gaussian blur. The DMOS values in the database were calculated from 48000 data which are provided by 60 subjects. Ten classical image quality assessment algorithms were tested on the MP2020 database. The experimental results show that the existing image quality assessment algorithms, which are widely used, are not applicable to the macro photography images. Therefore, MP2020 would contribute to the improvement of existing algorithms and the development of new algorithms. MP2020 has been uploaded to GitHub for download.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Color Image Database HTID for Verification of No-Reference Metrics: Peculiarities and Preliminary Results

Cited by 25 publications

References 23 publications

On the relation between statistical learning and perceptual distances

On the relation between statistical learning and perceptual distances

No‐reference image quality assessment based on multiscale feature representation

MP2020: Visual quality assessment database for macro photography images

Contact Info

Product

Resources

About