您的位置:山东大学 -> 科技期刊社 -> 《山东大学学报(工学版)》

山东大学学报(工学版) ›› 2015, Vol. 45 ›› Issue (3): 15-21.doi: 10.6040/j.issn.1672-3961.3.2014.172

• 机器学习与数据挖掘 • 上一篇    下一篇

一种基于Shearlet变换的图像质量客观评价方法

任玉玲, 路文, 徐红强, 何立火   

  1. 西安电子科技大学电子工程学院, 陕西 西安 710071
  • 收稿日期:2014-10-08 修回日期:2015-05-11 出版日期:2015-06-20 发布日期:2014-10-08
  • 通讯作者: 路文(1982- ),男,陕西咸阳人,副教授,博士,主要研究方向为视觉信息感知. E-mail:luwen@mail.xidian.edu.cn E-mail:luwen@mail.xidian.edu.cn
  • 作者简介:任玉玲(1990- ),女,河南商丘人,硕士研究生,主要研究方向为图像质量评价. E-mail:renyuling@stu.xidian.edu.cn
  • 基金资助:
    国家自然科学基金资助项目(61125204, 61372130, 61432014);中央高校基本科研业务费专项资金资助项目(BDY081426, JB140214);陕西省科技新星专项资金资助项目(2014KJXX-47))

An image quality assessment method based on Shearlet transform

REN Yuling, LU Wen, XU Hongqiang, HE Lihuo   

  1. School of Electronic Engineering, Xidian University, Xi'an 710071, Shaanxi, China
  • Received:2014-10-08 Revised:2015-05-11 Online:2015-06-20 Published:2014-10-08

摘要: 提出一种新的图像质量评价方法,将Shearlet变换捕捉视觉感知特征的能力和人类视觉系统的感知特性相结合来描述各种失真引起的图像质量的变化。该评价方法首先对参考图像和失真图像进行Shearlet分解,再对分解得到的不同尺度下的子带系数进行对比敏感度掩膜。然后根据由参考图像子带系数确定的感知阈值来计算参考图像和失真图像的各个子带中可感知到的系数所占的比例。最后通过比较失真图像相对于参考图像可感知到的系数所占比例的变化程度,综合得到图像质量的客观评价。分别在LIVE数据库和不同失真程度的图像集上对本研究算法进行有效性和合理性实验。实验表明本研究所获得的客观质量评价结果与人类的主观质量评价具有较高的一致性,能够很好地反映人类的主观感受。

关键词: 人类视觉系统, 图像质量评价, 方向滤波, 视觉感知, 多尺度几何分析, Shearlet变换

Abstract: An objective image quality assessment metric was proposed by combing the ability of shearlet transform to capture the visual perception feature and the properties of human visual system to describe the degradation of image quality. First, the shearlet transformation was applied to reference and distorted images to obtain the subband coefficients of different scales, and then the contrast sensitivity masking was employed to obtain the subband coefficients of different scales of same perceptual importance. Second, the proportion of perceived coefficients of reference and distorted images was calculated according to the perception threshold, which was obtained from the subband coefficients of reference image. Finally, the objective image quality assessment was acquired by comparing the differences of the proportion of perceived coefficients between reference and distorted images. Tests were done on LIVE database and image sets of distortion at different levels to verify the rationality and validity of the proposed method. Experimental results illustrated that the proposed method had a good consistency with the subjective assessment of human beings, thus could be used to describe the visual perception of the image effectively.

Key words: image quality assessment, visual perception, multiscale geometric analysis, directional filter, Shearlet transformation, human visual system

中图分类号: 

  • TN911.73
[1] WANG Z, BOVIK A C. Modern image quality assessment[M]. New York, USA:Morgan and Claypool Publishing Company, 2006.
[2] CHITPRASERT B, RAO K R. Human visual weighted progressive image transmission[J]. IEEE Transaction on Communications, 1990, 38(7):1040-1044.
[3] PARK H, HAR D H. Subjective image quality assessment based on objective image quality measurement factors[J]. IEEE Transaction on Consumer Electronics, 2011, 57(3):1176-1184.
[4] HORE A, ZIOU D. Image quality metrics:PSNR vs. SSIM[C]//2010 20th International Conference on Pattern Recognition. Istanbul, Turkey:IEEE, 2010:2366-2369.
[5] WANG Z, SIMONCELLI E P, BOVIK A C. Multiscale structural similarity for image quality assessment[C]//the Thirty-Seventh Asilomar Conference on Signals, Systems and Computers. Asilomar, USA:IEEE, 2003:1398-1402.
[6] WANG Z, SIMONCELLI E P. Reduced-reference image quality assessment using a wavelet-domain natural image statistic model[C]//17th Annual Symposium on Electronic Imaging. New York, USA:SPIE, 2005:149-159.
[7] LIN M, SONGNAN L, KING N N, et al. Reduced-reference image quality assessment in reorganized DCT domain[J]. Signal Processing:Image Communication, 2013, 28(8):884-902.
[8] WU J, LIN W, SHI G, et al. Image quality assessment with degradation on spatial structure[J]. Signal Processing Letters, IEEE, 2014, 21(4):437-440.
[9] GAO X, LU W, LI X, et al. Wavelet-based contourlet in quality evaluation of digital images[J]. Neurocomputing, 2008, 72(1):378-385.
[10] TAO D, LI X, LU W, et al. Reduced-reference IQA in contourlet domain[J]. IEEE Transaction Systems, Man and Cybernetics:Part B, 2009, 39(6):1623-1627.
[11] SCHWARTZ W R, SILVA R D, DAVIS L S, et al. A novel feature descriptor based on the shearlet transform[C]//18th IEEE International Conference on Image Processing. Brussels, Belgium:IEEE, 2011:1033-1036.
[12] LIM W Q. The discrete shearlet transform:a new directional transform and compactly supported shearlet frames[J]. IEEE Transaction on Image Processing, 2010, 19(5):1166-1180.
[13] NEGIP S, LABATE D. 3-D discrete shearlet transform and video processing[J]. IEEE Transaction on Image Processing, 2012, 21(6):2944-2954.
[14] 高新波, 路文. 视觉信息质量评价方法[M]. 西安:西安电子科技大学出版社, 2010.
[15] JACQUES L, DUVAL L, CHAUX C, et al. A panorama on multiscale geometric representations, intertwining spatial, directional and frequency selectivity[J]. Signal Processing, 2011, 91(12):2699-2730.
[16] GAO X, LU W, TAO D, et al. Image quality assessment based on multiscale geometric analysis[J]. IEEE Transaction on Image Processing, 2009, 18(7):1409-1423.
[17] JIAO L, TAN S. Development and prospect of image multiscale geometric analysis[J]. Acta Electronica Sinica, 2003, 31(12A):1975-1981.
[18] DAUBECHIES I. The wavelet transform, time-frequency localization and signal analysis[J]. IEEE Transaction on Information Theory, 1990, 36(5):961-1005.
[19] DO M N, VETTERLI M. The contourlet transform:an efficient directional multiresolution image representation[J]. IEEE Transaction on Image Processing, 2005, 14(12):2091-2106.
[20] CHAI Y, LI H, ZHANG X. Multifocus image fusion based on features contrast of multiscale products in nonsubsampled contourlet transform domain[J]. Optik-Inter. Journal for Light and Electron Optics, 2012, 123(7):569-581.
[21] LIU H, HEYNDERICKX I. Visual attention in objective image quality assessment:based on eye-tracking data[J]. IEEE Transaction on Circuits and Systems for Video Technology, 2011, 21(7):971-982.
[22] EASLEY G, LABATE D, LIM W Q. Sparse directional image representations using the discrete shearlet transform[J]. Applied and Computational Harmonic Analysis, 2008, 25(1):25-46.
[23] GUO K, LABATE D. Optimally sparse multidimensional representation using shearlets[J]. SIAM Journal on Mathematical Analysis, 2007, 39(1):298-318.

[24] MILOSLAVSKI M, HO Y S. Zerotree wavelet image coding based on the human visual system model[C]//The 1998 IEEE Asia-Pacific Conference on Circuits and Systems. Chiangmai, Thailand:IEEE, 1998:57-60.
[1] 邹国锋,傅桂霞,李震梅,李海涛,王科俊. 融合二级评价指标的人脸图像质量评价方法[J]. 山东大学学报(工学版), 2016, 46(2): 6-13.
[2] 刘一方1,2, 张云峰1,2*, 迟静1,2,张彩明1,2. 基于SSLUT的颜色空间转换的快速算法[J]. 山东大学学报(工学版), 2013, 43(1): 41-47.
[3] 梁敏瑜, 孙权森*. 基于结构特征的图像质量评价模型[J]. 山东大学学报(工学版), 2012, 42(3): 52-56.
[4] 刘志军. 基于DCT域多通道彩色图像盲检水印算法[J]. 山东大学学报(工学版), 2011, 41(3): 31-35.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!