首页 > 论文 > 激光与光电子学进展 > 56卷 > 18期(pp:181006--1)

四元数小波变换优化单目图的无参考立体图像质量评价

No-Reference Stereo Image Quality Assessment of Cyclopean Images Optimized Using Quaternion Wavelet Transform

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

摘要

通过四元数小波变换分解立体图像的左右视图,获取不同尺度不同方向的幅值相位信息,并结合人眼视觉特性生成单目图;对左右视图和单目图作亮度去均值对比度归一化(MSCN)处理,获取MSCN系数图,采用广义高斯分布模型拟合MSCN系数和MSCN四方向邻域系数乘积,提取统计参数特征(联合峰度、偏度、标准偏差和能量),组成特征向量,通过XGBoost模型预测图像质量感知得分。结果表明,所提立体图像质量评价算法在LIVE3D图像库上优于其他方法,并且运行速度得到大幅度提高。

Abstract

First, the left and right views of stereo images are decomposed by quaternion wavelet transform to obtain the amplitude and phase information of different scales and directions, and then cyclopean images are generated by combining human visual characteristics. The left views, right views, and cyclopean images are processed via mean subtracted contrast normalization (MSCN). The MSCN coefficient map is then obtained. The MSCN coefficient and the product of MSCN four-direction neighborhood coefficients are fitted via a generalized Gauss distribution model to extract statistical parameter features. The feature vectors are formed by combining the kurtosis, skewness, standard deviation, and energy. The image quality perception score is then predicted using the XGBoost model. Experimental results show that the proposed stereo image quality assessment algorithm is superior to other reported methods in the LIVE 3D image database and it greatly improves the running speed.

Newport宣传-MKS新实验室计划
补充资料

DOI:10.3788/LOP56.181006

所属栏目:图像处理

基金项目:国家自然科学基金、江苏省自然科学基金;

收稿日期:2019-02-27

修改稿日期:2019-04-09

网络出版日期:2019-09-01

作者单位    点击查看

李一凡:江南大学物联网工程学院, 江苏 无锡 214166
李朝锋:上海海事大学物流科学与工程研究院, 上海 200135
桑庆兵:江南大学物联网工程学院, 江苏 无锡 214166

联系人作者:李朝锋(wxlichaofeng@126.com); 桑庆兵( sangqb@163.com);

备注:国家自然科学基金、江苏省自然科学基金;

【1】Zhao W Z and Qin S Y. Image quality assessment and some solving approaches to current issues. Laser & Optoelectronics Progress. 47(4), (2010).
赵文哲, 秦世引. 图像质量评价的研究进展和若干问题的解决途径. 激光与光电子学进展. 47(4), (2010).

【2】Hou C P and Lin H H. Stereoscopic image quality assessment based on wavelet transform and structure characteristics. Laser & Optoelectronics Progress. 55(6), (2018).
侯春萍, 林洪湖. 基于小波变换与结构特征的立体图像质量评价. 激光与光电子学进展. 55(6), (2018).

【3】Chen M J, Su C C, Kwon D K et al. Full-reference quality assessment of stereopairs accounting for rivalry. Signal Processing: Image Communication. 28(9), 1143-1155(2013).

【4】Chen M J, Cormack L K and Bovik A C. No-reference quality assessment of natural stereopairs. IEEE Transactions on Image Processing. 22(9), 3379-3391(2013).

【5】Shao F, Lin W S, Gu S B et al. Perceptual full-reference quality assessment of stereoscopic images by considering binocular visual characteristics. IEEE Transactions on Image Processing. 22(5), 1940-1953(2013).

【6】Su C C, Cormack L K and Bovik A C. Oriented correlation models of distorted natural images with application to natural stereopair quality evaluation. IEEE Transactions on Image Processing. 24(5), 1685-1699(2015).

【7】Appina B, Khan S and Channappayya S S. No-reference stereoscopic image quality assessment using natural scene statistics. Signal Processing: Image Communication. 43, 1-14(2016).

【8】Zhang W, Qu C F, Ma L et al. Learning structure of stereoscopic image for no-reference quality assessment with convolutional neural network. Pattern Recognition. 59, 176-187(2016).

【9】Zhou W J, Yu L, Qiu W W et al. Utilizing binocular vision to facilitate completely blind 3D image quality measurement. Signal Processing. 129, 130-136(2016).

【10】Xue X B, Yu M and He M L. Stereoscopic image-quality-assessment method based on visual cell model. Laser & Optoelectronics Progress. 53(4), (2016).
薛小波, 郁梅, 何美伶. 基于仿视觉细胞模型的立体图像质量评价方法. 激光与光电子学进展. 53(4), (2016).

【11】Yue J, Liu G J and Fu H. Color image quality assessment based on quaternion spectral residual. Laser & Optoelectronics Progress. 56(3), (2019).
岳靖, 刘国军, 付浩. 四元数谱余量彩色图像质量评价. 激光与光电子学进展. 56(3), (2019).

【12】Chan W L, Choi H and Baraniuk R G. Coherent multiscale image processing using dual-tree quaternion wavelets. IEEE Transactions on Image Processing. 17(7), 1069-1082(2008).

【13】Li C R, Li J P and Fu B. Magnitude-phase of quaternion wavelet transform for texture representation using multilevel copula. IEEE Signal Processing Letters. 20(8), 799-802(2013).

【14】Gai S, Yang G W and Zhang S. Multiscale texture classification using reduced quaternion wavelet transform. AEU-International Journal of Electronics and Communications. 67(3), 233-241(2013).

【15】Chai P F, Luo X Q and Zhang Z C. Image fusion using quaternion wavelet transform and multiple features. IEEE Access. 5, 6724-6734(2017).

【16】Oppenheim A V and Lim J S. The importance of phase in signals. Proceedings of the IEEE. 69(5), 529-541(1981).

【17】Hayes M, Lim J and Oppenheim A. Signal reconstruction from phase or magnitude. IEEE Transactions on Acoustics, Speech, and Signal Processing. 28(6), 672-680(1980).

【18】Vilankar K P, Vasu L and Chandler D M. On the perception of band-limited phase distortion in natural scenes. Proceedings of SPIE. 7865, (2011).

【19】Mittal A, Moorthy A K and Bovik A C. No-reference image quality assessment in the spatial domain. IEEE Transactions on Image Processing. 21(12), 4695-4708(2012).

【20】Chen T Q and Guestrin C. XGBoost: a scalable tree boosting system. [C]∥KDD 2016: 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 13-17, 2016, San Francisco, California, USA. New York: ACM. 785-794(2016).

引用该论文

Yifan Li,Chaofeng Li,Qingbing Sang. No-Reference Stereo Image Quality Assessment of Cyclopean Images Optimized Using Quaternion Wavelet Transform[J]. Laser & Optoelectronics Progress, 2019, 56(18): 181006

李一凡,李朝锋,桑庆兵. 四元数小波变换优化单目图的无参考立体图像质量评价[J]. 激光与光电子学进展, 2019, 56(18): 181006

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