互补色小波域图像质量盲评价方法

doi:10.3969/j.issn.0372-2112.2019.04.002

PDF(832 KB)

电子学报 ›› 2019, Vol. 47 ›› Issue (4) : 775-783. DOI: 10.3969/j.issn.0372-2112.2019.04.002

学术论文

互补色小波域图像质量盲评价方法

陈扬, 李旦, 张建秋

作者信息 +

Blind Image Quality Assessment with Complementary Color Wavelet Transform

CHEN Yang, LI Dan, ZHANG Jian-qiu

Author information +

文章历史 +

摘要

图像色彩空间的RGB通道具有密切的关系，图像质量的改变会改变这样的关系.然而传统图像质量评价方法大多基于灰度图像统计特性，忽略了颜色通道间关系信息.为充分利用颜色信息，本文基于新近提出的互补色小波变换提出一种图像质量盲评价方法.文章建立了图像互补色域自然场景统计、多尺度和方向性能量分布等模型.分析表明：这些模型不仅涵盖了传统灰度方法所能描述的信息，而且还能借助于互补色来有效表示彩色图像各通道之间的信息联系，提供表征图像质量的一组高效特征.基于这些特征，我们提出的图像质量盲评价的方法能有效提取图像的失真统计特征，能给出与人眼主观评价图像质量结果保持高度一致、优于现有文献报道盲方法、且可与非盲（全参考）方法相比拟的评价结果.

Abstract

In the image color space,the RGB channels have strong correlations.The quality change of an image will lead to the change of channel correlations.However,most traditional image quality assessment (IQA) methods,based on grayscale image statistics,ignore such correlation information among color channels.In this paper,to utilize the color information,we propose a blind IQA method based on the recent proposed complementary color wavelet transform (CCWT).We provide models for the complementary color nature scene statistics,multi-resolution and multi-directionality energy distributions of an image.The analysis shows that our models not only cover the information of traditional methods,but also provide the relation information among color channels.A group of high-efficiency image quality features is then given.Based on these features,our blind IQA method can effectively extract the distortion statistic features and provide assessment results.Our IQA results are agreeing with the human subjective,better than the state-of-the-art blind IQA results,and close to the full-reference ones.

导出引用

陈扬, 李旦, 张建秋. 互补色小波域图像质量盲评价方法[J]. 电子学报, 2019, 47(4): 775-783. https://doi.org/10.3969/j.issn.0372-2112.2019.04.002

CHEN Yang, LI Dan, ZHANG Jian-qiu. Blind Image Quality Assessment with Complementary Color Wavelet Transform[J]. Acta Electronica Sinica, 2019, 47(4): 775-783. https://doi.org/10.3969/j.issn.0372-2112.2019.04.002

中图分类号： TN911.72

参考文献

[1] WANG Z,BOVIK A C,SHEIKH H R,et al. Image quality assessment:from error visibility to structural similarity[J]. IEEE Transactions on Image Processing,2004,13(4):600-612.
[2] SHEIKH H R,BOVIK A C. Image information and visual quality[A]. Proceedings of IEEE International Conference on Acoustics,Speech,and Signal Processing (ICASSP'04)[C]. US:IEEE,2004,3:iii-709.
[3] LI Q,WANG Z. Reduced-reference image quality assess-ment using divisive normalization-based image representa-tion[J]. IEEE Journal of Selected Topics in Signal Pro-cessing,2009,3(2):202-211.
[4] SAAD M A, BOVIK A C, CHARRIER C. Blind image quality assessment:A natural scene statistics approach in the DCT domain[J]. IEEE Transactions on Image Process-ing,2012,21(8):3339-3352.
[5] MOORTHY A K,BOVIK A C. Blind image quality assess-ment:From natural scene statistics to perceptual quality[J]. IEEE Transactions on Image Processing, 2011, 20(12):3350-3364.
[6] 黄虹,张建秋. 一个图像质量盲评估的统计测度[J]. 电子学报,2014,42(7):1419-1423. HUANG Hong,ZHANG Jian-qiu. A statistical measure for blind image quality assessment[J]. Acta Electronica Sini-ca,2014,42(7):1419-1423. (in Chinese)
[7] 米曾真. 小波域中CSF频率与方向加权的图像质量评价方法[J]. 电子学报,2014,42(7):1273-1276. MI Zeng-zhen. Image quality evaluation method based on frequency and direction weighted to CSF in wavelet domain[J]. Acta Electronica Sinica,2014,42(7):1273-1276. (in Chinese)
[8] 郑江云,江巨浪. 基于小波第二级系数误差的图像质量评价模型[J]. 电子学报,2012,40(3):559-563. ZHENG Jiang-yun, JIANG Ju-lang. A model of image quality assessment based on wavelet second coefficient er-ror[J]. Acta Electronica Sinica,2012,40(3):559-563.(in Chinese)
[9] LIU L, DONG H, HUANG H, et al. No-reference image quality assessment in curvelet domain[J]. Signal Process-ing:Image Communication,2014,29(4):494-505.
[10] 沈军民,李俊峰,戴文战. 结合结构信息和亮度统计的无参考图像质量评价[J]. 电子学报,2016,44(4):804-812. SHEN Jun-min, LI Jun-feng, DAI Wen-zhan. No-refer-ence image quality assessment based on structure informa-tion and luminance statistics[J]. Acta Electronica Sinica, 2016,44(4):804-812. (in Chinese)
[11] 贾旭,曹玉东,孙福明,等. 基于无参考质量评价模型的静脉图像采集方法[J]. 电子学报,2015,43(2):236-241. JIA Xu,CAO Yu-dong,SUN Fu-ming,et al. Vein image acquisition method based on quality assessment model without reference[J]. Acta Electronica Sinica, 2015, 43(2):236-241. (in Chinese)
[12] CHEN M J,BOVIK A C. No-reference image blur assess-ment using multiscale gradient[J]. EURASIP Journal on Image and Video Processing,2011,2011(1):3.
[13] LIU L, LIU B, HUANG H, et al. No-reference image quality assessment based on spatial and spectral entropies[J]. Signal Processing:Image Communication,2014,29(8):856-863.
[14] 李俊峰. 基于RGB色彩空间自然场景统计的无参考图像质量评价[J]. 自动化学报, 2015, 41(9):1601-1615. LI Jun-feng. No-reference image quality assessment based on natural scene statistics in RGB color space[J]. Acta Automatica Sinica,2015,41(9):1601-1615. (in Chi-nese)
[15] LIU L,LIU B,SU C C,et al. Binocular spatial activity and reverse saliency driven no-reference stereopair quality assessment[J]. Signal Processing:Image Communica-tion,2017,58:287-299.
[16] CHEN Y, LI D, ZHANG J Q. Complementary color wavelet:A novel tool for the color image/video analysis and processing[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, DOI:10. 1109/TCSVT. 2017. 2776239.
[17] SHEIKH H R,WANG Z,CORMACK L,et al. LIVE Im-age Quality Assessment Database Release 2(2005)[OL]. Available:http://live.ece.utexas.edu/research/quality,2011-9-1.
[18] PRIDMORER W. Complementary colors theory of color vision:Physiology,color mixture,color constancy and col-or perception[J]. Color Research & Application,2011,36(6):394-412.
[19] PRIDMORE R W. Complementary colors:The structure of wavelength discrimination,uniform hue,spectral sensi-tivity,saturation,chromatic adaptation, and chromatic in-duction[J]. Color Research & Application,2009,34(3):233-252.
[20] MITTAL A,MOORTHY A K,BOVIK A C. No-reference image quality assessment in the spatial domain[J]. IEEE Transactions on Image Processing, 2012, 21(12):4695-4708.
[21] MOORTHY A K,BOVIK A C. A two-step framework for constructing blind image quality indices[J]. IEEE Signal Processing Letters,2010,17(5):513-516.
[22] MITTAL A,SOUNDARARAJAN R,BOVIK A C. Mak-ing a "completely blind" image quality analyzer[J]. IEEE Signal Processing Letters,2013,20(3):209-212.
[23] WAINWRIGHT M J,SIMONCELLI E P. Scale mixtures of Gaussians and the statistics of natural images[A]. Ad-vances in Neural Information Processing Systems[C]. US:ACM,2000. 855-861.
[24] XUE W,MOU X,ZHANG L,et al. Blind image quality assessment using joint statistics of gradient magnitude and Laplacian features[J]. IEEE Transactions on Image Pro-cessing,2014,23(11):4850-4862.
[25] LIU L,HUA Y,ZHAO Q,et al. Blind image quality as-sessment by relative gradient statistics and adaboosting neural network[J]. Signal Processing:Image Communica-tion,2016,40:1-15.
[26] BOSSE S,MANIRY D,WIEGAND T,et al. A deep neu-ral network for image quality assessment[A]. IEEE Inter-national Conference on Image Processing (ICIP)[C]. US:IEEE,2016. 3773-3777.
[27] CHANG C C,LIN C J. LIBSVM:A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology (TIST),2011,2(3):27.