JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering

Accepted manuscript available online (unedited version)

No-reference noisy image quality assessment incorporating features of entropy, gradient, and kurtosis

Author(s): Heng Yao, Ben Ma, Mian Zou, Dong Xu, Jincao Yao
Affiliation(s): School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China; more
Corresponding email(s): hyao@usst.edu.cn, xudong@zjcc.org.cn, yaojc@zjcc.org.cn
Key Words: Noisy image quality assessment, Noise estimation, Kurtosis, Human visual system, Support vector regression

Share this article to： More <<< Previous Paper \|Next Paper >>>

Heng Yao, Ben Ma, Mian Zou, Dong Xu, Jincao Yao. No-reference noisy image quality assessment incorporating features of entropy, gradient, and kurtosis[J]. Frontiers of Information Technology & Electronic Engineering,in press.https://doi.org/10.1631/FITEE.2000716

@article{title="No-reference noisy image quality assessment incorporating features of entropy, gradient, and kurtosis",
author="Heng Yao, Ben Ma, Mian Zou, Dong Xu, Jincao Yao",
journal="Frontiers of Information Technology & Electronic Engineering",
year="in press",
publisher="Zhejiang University Press & Springer",
doi="https://doi.org/10.1631/FITEE.2000716"
}

%0 Journal Article
%T No-reference noisy image quality assessment incorporating features of entropy, gradient, and kurtosis
%A Heng Yao
%A Ben Ma
%A Mian Zou
%A Dong Xu
%A Jincao Yao
%J Frontiers of Information Technology & Electronic Engineering
%P 1565-1582
%@ 2095-9184
%D in press
%I Zhejiang University Press & Springer
doi="https://doi.org/10.1631/FITEE.2000716"

TY - JOUR
T1 - No-reference noisy image quality assessment incorporating features of entropy, gradient, and kurtosis
A1 - Heng Yao
A1 - Ben Ma
A1 - Mian Zou
A1 - Dong Xu
A1 - Jincao Yao
J0 - Frontiers of Information Technology & Electronic Engineering
SP - 1565
EP - 1582
%@ 2095-9184
Y1 - in press
PB - Zhejiang University Press & Springer
ER -
doi="https://doi.org/10.1631/FITEE.2000716"

Abstract
Chinese Summary
Academic Network
Reviewer Comment

Abstract: Noise is the most common type of image distortion affecting human visual perception. In this paper, we propose a no-reference image quality assessment (IQA) method for noisy images incorporating the features of entropy, gradient, and kurtosis. Specifically, image noise estimation is conducted in the discrete cosine transform domain based on skewness invariance. In the principal component analysis domain, kurtosis feature is obtained by statistically counting the significant differences between images with and without noise. In addition, both the consistency between the entropy and kurtosis features and the subjective scores are improved by combining them with the gradient coefficient. support vector regression is applied to map all extracted features into an integrated scoring system. The proposed method is evaluated in three mainstream databases (i.e., LIVE, TID2013, and CSIQ), and the results demonstrate the superiority of the proposed method according to the Pearson linear correlation coefficient which is the most significant indicator in IQA.

结合熵、梯度、峰度特征的无参考噪声图像质量评价

姚恒¹，马奔²，邹勔²，徐栋^3,4，姚劲草^3,4
¹上海理工大学光电信息与计算机工程学院，中国上海市，200093
²上海理工大学机械工程学院，中国上海市，200093
³中国科学院大学附属肿瘤医院（浙江省肿瘤医院），中国杭州市，310000
⁴中国科学院肿瘤与基础医学研究所，中国杭州市，310000
摘要：噪声是影响人类视觉感知最常见的图像失真类型。本文提出一种基于熵、梯度和峰度特征的无参考图像质量评估方法。具体来说，基于偏度不变性在离散余弦变换域进行图像噪声估计，进一步计算得到熵特征。在主成分分析变换域，通过统计有噪声图像与无噪声图像之间的显著差异得到峰度特征。此外，将熵和峰度特征与梯度系数结合，提高熵和峰度特征与主观得分之间的一致性。通过不同方向的滤波器对图像进行梯度特征提取，最后支持向量回归将所有提取的特征映射到综合评分系统中。为验证算法性能，在3个主流数据库（即LIVE、TID2013以及CSIQ）中对该方法进行评价。实验结果验证了该方法的优越性，尤其是在反映预测精度的皮尔逊线性相关系数方面的突出性能。

关键词组：噪声图像质量评价；噪声估计；峰度；人类视觉系统；支持向量回归

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]Bosse S, Maniry D, Wiegand T, et al., 2016. A deep neural network for image quality assessment. Proc IEEE Int Conf on Image Processing, p.3773-3777.

[2]Buczkowski M, 2018. Non-reference image quality assessment based on noise estimation. Proc 25^th Int Conf on Systems, Signals and Image Processing, p.1-4.

[3]Chang CC, Lin CJ, 2011. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol, 2(3):27.

[4]Chen DQ, Wang YZ, Gao W, 2020. No-reference image quality assessment: an attention driven approach. IEEE Trans Image Process, 29:6496-6506.

[5]Deng CW, Wang SG, Bovik AC, et al., 2020. Blind noisy image quality assessment using sub-band kurtosis. IEEE Trans Cybern, 50(3):1146-1156.

[6]Ding Y, Li N, Zhao Y, et al., 2016. Image quality assessment method based on nonlinear feature extraction in kernel space. Front Inform Technol Electron Eng, 17(10):1008-1017.

[7]Dong L, Zhou JT, Tang YY, 2017. Noise level estimation for natural images based on scale-invariant kurtosis and piecewise stationarity. IEEE Trans Image Process, 26(2):1017-1030.

[8]Gu K, Zhai GT, Yang XK, et al., 2015. Using free energy principle for blind image quality assessment. IEEE Trans Multim, 17(1):50-63.

[9]Guo R, Shen XJ, Dong XY, et al., 2020. Multi-focus image fusion based on fully convolutional networks. Front Inform Technol Electron Eng, 21(7):1019-1033.

[10]Hu B, Li LD, Wu JJ, et al., 2020. Subjective and objective quality assessment for image restoration: a critical survey. Signal Process Image Commun, 85:115839.

[11]Huang XT, Chen L, Tian J, et al., 2014. Blind noisy image quality assessment using block homogeneity. Comput Electr Eng, 40(3):796-807.

[12]Jiang XH, Shen LQ, Yu LW, et al., 2020. No-reference screen content image quality assessment based on multi-region features. Neurocomputing, 386:30-41.

[13]Kennedy J, Eberhart R, 1995. Particle swarm optimization. Proc Int Conf on Neural Networks, p.1942-1948.

[14]Kong XF, Li K, Yang QX, et al., 2013. A new image quality metric for image auto-denoising. Proc IEEE Int Conf on Computer Vision, p.2888-2895.

[15]Larson EC, Chandler DM, 2010. Most apparent distortion: full-reference image quality assessment and the role of strategy. J Electron Image, 19(1):011006.

[16]Li LD, Xia WH, Fang YM, et al., 2016a. Color image quality assessment based on sparse representation and reconstruction residual. J Vis Commun Image Represent, 38: 550-560.

[17]Li LD, Lin WS, Wang XS, et al., 2016b. No-reference image blur assessment based on discrete orthogonal moments. IEEE Trans Cybern, 46(1):39-50.

[18]Li LD, Xia WH, Lin WS, et al., 2017. No-reference and robust image sharpness evaluation based on multiscale spatial and spectral features. IEEE Trans Multim, 19(5):1030-1040.

[19]Li PY, Lo KT, 2018. A content-adaptive joint image compression and encryption scheme. IEEE Trans Multim, 20(8):1960-1972.

[20]Li QH, Lin WS, Fang YM, 2017. BSD: blind image quality assessment based on structural degradation. Neurocomputing, 236:93-103.

[21]Liu M, Zhai GT, Zhang ZY, et al., 2014. Blind image quality assessment for noise. Proc IEEE Int Symp on Broadband Multimedia Systems and Broadcasting, p.1-5.

[22]Lyu SW, Pan XY, Zhang X, 2014 Exposing region splicing forgeries with blind local noise estimation. Int J Comput Vis, 110(2):202-221.

[23]Ma B, Yao JC, Le YF, et al., 2020. Efficient image noise estimation based on skewness invariance and adaptive noise injection. IET Image Process, 14(7):1393-1401.

[24]Min XK, Zhai GT, Gu K, et al., 2018. Blind image quality estimation via distortion aggravation. IEEE Trans Broadcast, 64(2):508-517.

[25]Mittal A, Moorthy AK, Bovik AC, 2012. No-reference image quality assessment in the spatial domain. IEEE Trans Image Process, 21(12):4695-4708.

[26]Mittal A, Soundararajan R, Bovik AC, 2013. Making a “completely blind” image quality analyzer. IEEE Signal Process Lett, 20(3):209-212.

[27]Moorthy AK, Bovik AC, 2011. Blind image quality assessment: from natural scene statistics to perceptual quality. IEEE Trans Image Process, 20(12):3350-3364.

[28]Ospina-Borras JE, Restrepo HDB, 2016. Non-reference assessment of sharpness in blur/noise degraded images. J Vis Commun Image Represent, 39:142-151.

[29]Oszust M, 2019. No-reference quality assessment of noisy images with local features and visual saliency models. Inform Sci, 482:334-349.

[30]Pan CH, Xu Y, Yan YC, et al., 2016. Exploiting neural models for no-reference image quality assessment. Proc Visual Communications and Image Processing, p.1-4.

[31]Ponomarenko N, Ieremeiev O, Lukin V, et al., 2013. A new color image database TID2013: innovations and results. Proc 15^th Int Conf on Advanced Concepts for Intelligent Vision Systems, p.402-413.

[32]Saad MA, Bovik AC, Charrier C, 2012. Blind image quality assessment: a natural scene statistics approach in the DCT domain. IEEE Trans Image Process, 21(8):3339-3352.

[33]Sheikh HR, Sabir MF, Bovik AC, 2006. A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Trans Image Process, 15(11):3440-3451.

[34]Shen LL, Hang N, Hou CP, 2020. Feature-segmentation strategy based convolutional neural network for no-reference image quality assessment. Multim Tool Appl, 79(17-18):11891-11904.

[35]Tang LJ, Li LD, Sun KZ, et al., 2017. An efficient and effective blind camera image quality metric via modeling quaternion wavelet coefficients. J Vis Commun Image Represent, 49:204-212.

[36]Tang ZJ, Huang ZQ, Yao H, et al., 2018. Perceptual image hashing with weighted DWT features for reduced-reference image quality assessment. Comput J, 61(11):1695-1709.

[37]Video Quality Experts Group, 2003. Final Report from the Video Quality Experts Group on the Validation of Objective Models of Video Quality Assessment, Phase II (fr_tv2). http://www.vqeg.org

[38]Wang Q, Chu J, Xu L, et al., 2016. A new blind image quality framework based on natural color statistic. Neurocomputing, 173:1798-1810.

[39]Wang Z, Bovik AC, Sheikh HR, et al., 2004. Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process, 13(4):600-612.

[40]Wu JJ, Zhang M, Li LD, et al., 2019. No-reference image quality assessment with visual pattern degradation. Inform Sci, 504:487-500.

[41]Xu L, Huang G, Chen QL, et al., 2020. An improved method for image denoising based on fractional-order integration. Front Inform Technol Electron Eng, 21(10):1485-1493.

[42]Ye P, Kumar J, Kang L, et al., 2012. Unsupervised feature learning framework for no-reference image quality assessment. Proc IEEE Conf on Computer Vision and Pattern Recognition, p.1098-1105.

[43]Zhai GT, Wu XL, 2011. Noise estimation using statistics of natural images. Proc 18^th IEEE Int Conf on Image Processing, p.1857-1860.

[44]Zhai GT, Wu XL, Yang XK, et al., 2012. A psychovisual quality metric in free-energy principle. IEEE Trans Image Process, 21(1):41-52.

[45]Zhai GT, Kaup A, Wang J, et al., 2015. A dual-model approach to blind quality assessment of noisy images. APSIPA Trans Signal Inform Process, 4:e4.

[46]Zhang L, Zhang L, Bovik AC, 2015. A feature-enriched completely blind image quality evaluator. IEEE Trans Image Process, 24(8):2579-2591.

[47]Zhou WJ, Yu L, Qiu WW, et al., 2017. Local gradient patterns (LGP): an effective local-statistical-feature extraction scheme for no-reference image quality assessment. Inform Sci, 397-398:1-14.

[48]Zhu HC, Li LD, Wu JJ, et al., 2020. MetaIQA: deep meta-learning for no-reference image quality assessment. IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.14143-14152.

[49]Zhu T, Karam L, 2014. A no-reference objective image quality metric based on perceptually weighted local noise. EURASIP J Image Video Process, 2014(1):1-8.

[50]Zoran D, Weiss Y, 2009. Scale invariance and noise in natural images. Proc IEEE Int Conf on Computer Vision, p.2209-2216.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

- Go to

结合熵、梯度、峰度特征的无参考噪声图像质量评价

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference