首页 > 论文 > 激光与光电子学进展 > 56卷 > 3期(pp:31009--1)

四元数谱余量彩色图像质量评价

Color Image Quality Assessment Based on Quaternion Spectral Residual

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

通过将参考图像与失真图像表示为纯四元数矩阵, 提出了一种用于检测两幅图像视觉显著性区域的四元数谱余量方法。将该方法与四元数梯度特征作为指标构建彩色图像质量评价方法, 并将视觉显著性作为评价指标的权值。利用Spearman等级相关系数(SROCC)、Kendall等级相关系数、Pearson线性相关系数及均方误差平方根4种客观评价指标在TID2013与CSIQ数据库中进行数值实验, 结果表明, 所提算法在TID2013上的SROCC值为0.8169, 且与人的主观评价相匹配。

Abstract

The quaternion spectral residual method for detecting the visual saliency regions of two images is proposed, by expressing the reference image and the distorted image as a pure quaternion matrix. Then both the method and the quaternion gradient features are employed to design color image quality evaluation, as well as visual saliency as the weight of the evaluation index. Numerical experiments are conducted on the TID2013 and CSIQ databases to calculate four kinds of objective evaluation indexes such as the Spearman rank correlation coefficient (SROCC), the Kendall rank correlation coefficient, the Pearson linear correlation coefficient, and the root mean squared error. The results show that the experimental SROCC value on TID2013 reaches 0.8169, which matches the subjective evaluation of humans.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP391.41

DOI:10.3788/lop56.031009

所属栏目:图像处理

基金项目:国家自然科学基金(61461043)、宁夏自然科学基金(2018AAC03014)

收稿日期:2018-08-29

修改稿日期:2018-09-08

网络出版日期:2018-09-18

作者单位    点击查看

岳靖:宁夏大学数学统计学院, 宁夏 银川 750021
刘国军:宁夏大学数学统计学院, 宁夏 银川 750021
付浩:宁夏大学数学统计学院, 宁夏 银川 750021

联系人作者:刘国军(liugj@nxu.edu.cn); 岳靖(yjing1995@163.com);

【1】Hou X D, Zhang L Q. Saliency detection: a spectral residual approach[C]∥Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 2007: 383267.

【2】Xu M, Zhang H L. Saliency detection with color contrast based on boundary information and neighbors[J]. Visual Computer, 2015, 31(3): 355-364.

【3】Zhang L, Li H Y. SR-SIM: a fast and high performance IQA index based on spectral residual[C]∥IEEE International Conference on Image Processing, 2012: 1473-1476.

【4】Zhang L, Shen Y, Li H Y. VSI: a visual saliency-induced index for perceptual image quality assessment[J]. IEEE Transactions on Image Processing, 2014, 23(10): 4270-4281.

【5】Zhang L, Zhang L, Mou X Q, et al. FSIM: a feature similarity index for image quality assessment[J]. IEEE Transactions on Image Processing, 2011, 20(8): 2378-2386.

【6】Ma Y M, Chen H Y, Liu G J. General mean pooling strategy for color image quality assessment[J]. Laser & Optoelectronics Progress, 2018, 55(2): 021007.
马月梅, 陈海英, 刘国军. 彩色图像质量评价的广义平均池化策略[J]. 激光与光电子学进展, 2018, 55(2): 021007.

【7】Pei S C, Cheng C M. A novel block truncation coding of color images using a quaternion-moment-preserving principle[J]. IEEE Transactions on Communications, 1997, 45(5): 583-595.

【8】Yu L C, Xu Y, Xu H T, et al. Quaternion-based sparse representation of color image[C]∥IEEE International Conference on Multimedia and Expo, 2013: 6607436.

【9】Jin L H, Song E M, Li L, et al. A quaternion gradient operator for color image edge detection[C]∥IEEE International Conference on Image Processing, 2013: 3040-3044.

【10】Zeng R, Wu J S, Shao Z H, et al. Color image classification via quaternion principal component analysis network[J]. Neurocomputing, 2016, 216: 416-428.

【11】Lan R S, Zhou Y C, Tang Y Y. Quaternionic weber local descriptor of color images[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2017, 27(2): 261-274.

【12】Gai S, Luo L M. Image denoising using normal inverse gaussian model in quaternion wavelet domain[J]. Multimedia Tools and Applications, 2015, 74(3): 1107-1124.

【13】Gai S, Yang G W, Wan M H, et al. Denoising color images by reduced quaternion matrix singular value decomposition[J]. Multidimensional Systems and Signal Processing, 2015, 26(1): 307-320.

【14】Angulo J. Structure tensor of colour quaternion image representations for invariant feature extraction[C]∥International Workshop on Computational Color Imaging, , 2009: 91-100.

【15】Xu H Y, Kong J, Jiang M. Human action recognition by representation 3D skeleton as points based on quaternion[J]. Laser & Optoelectronics Progress, 2018, 55(2): 021002.
徐海洋, 孔军, 蒋敏. 基于四元数3D骨骼表示的人体行为识别[J]. 激光与光电子学进展, 2018, 55(2): 021002.

【16】Wang Y Q, Zhu M. Maximum singular value method of quaternion matrix for evaluating color image quality[J]. Optics and Precision Engineering, 2013, 21(2): 469-478.
王宇庆, 朱明. 评价彩色图像质量的四元数矩阵最大奇异值方法[J]. 光学 精密工程, 2013, 21(2): 469-478.

【17】Kolaman A, Yadid-Pecht O. Quaternion structural similarity: a new quality index for color images[J]. IEEE Transactions on Image Processing, 2012, 21(4): 1526-1536.

【18】Wang Y, Wang Y Q, Gu H J, et al. Color image quality assessment method based on full quaternion structure similarity measure[J]. Journal of Optoelectronics·Laser, 2014, 25(10): 2033-2043.
王勇, 王宇庆, 顾海军, 等. 客观评价彩色图像质量的全四元数结构相似度方法[J]. 光电子·激光, 2014, 25(10): 2033-2043.

【19】Ponomarenko N, Ieremeiev O, Lukin V, et al. Color image database TID2013: peculiarities and preliminary results[C]∥IEEE European Workshop on Visual Information Processing, 2013: 106-111.

【20】Larson E C, Chandler D. Categorical image quality (CSIQ) database.[EB/OL].[2009-12-14] http:∥vision.eng.shizuoka.ac.jp/course/view.php?id=6.

【21】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.

【22】Zhang B, Sander P V, Bermak A. Gradient magnitude similarity deviation on multiple scales for color image quality assessment[C]∥IEEE International Conference on Acoustics, Speech and Signal Processing, 2017: 1253-1257.

【23】Chandler D M, Hemami S S. VSNR: a wavelet-based visual signal-to-noise ratio for natural images[J]. IEEE Transactions on Image Processing, 2007, 16(9): 2284-2298.

【24】Wang Z, Bovik A C, Lu L G. Why is image quality assessment so difficult?[C]∥IEEE International Conference on Acoustics, Speech, and Signal Processing, 2002: 3313-3316.

【25】Xue W F, Zhang L, Mou X Q, et al. Gradient magnitude similarity deviation: a highly efficient perceptual image quality index[J]. IEEE Transactions on Image Processing, 2014, 23(2): 684-695.

【26】Wang Z, Simoncelli E P, Bovik A C. Multiscale structural similarity for image quality assessment[C]∥IEEE Asilomar Conference on Signals, Systems & Computers, 2003: 1398-1402.

【27】Farias M C Q, Akamine W Y L. On performance of image quality metrics enhanced with visual attention computational models[J]. Electronics Letters, 2012, 48(11): 631-633.

【28】Wang Z, Li Q. Information content weighting for perceptual image quality assessment[J]. IEEE Transactions on Image Processing, 2011, 20(5): 1185-1198.

引用该论文

Yue Jing,Liu Guojun,Fu Hao. Color Image Quality Assessment Based on Quaternion Spectral Residual[J]. Laser & Optoelectronics Progress, 2019, 56(3): 031009

岳靖,刘国军,付浩. 四元数谱余量彩色图像质量评价[J]. 激光与光电子学进展, 2019, 56(3): 031009

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF