基于视觉阈值及通道融合的立体图像质量评价

郁梅; 孔真真; 朱江英

doi:10.3788/OPE.20132106.1605

您当前的位置：

首页 >

文章列表页 >

基于视觉阈值及通道融合的立体图像质量评价

信息科学 | 更新时间：2020-08-12

- 基于视觉阈值及通道融合的立体图像质量评价
- Stereoscopic image quality Assessment based on visual threshold and channel fusion
- 光学精密工程 2013年21卷第6期页码：1605-1612
- 作者机构：
  
  宁波大学信息科学与工程学院,浙江宁波,315211
- 作者简介：
- 基金信息：
  
  大尺寸有障碍空间角度与基面位置测量的关键技术();浙江省自然科学基金()
- DOI：10.3788/OPE.20132106.1605
  中图分类号： TP391.4
- 收稿日期：2012-12-04，
  
  修回日期：2013-02-01，
  
  网络出版日期：2013-06-20，
  
  纸质出版日期：2013-06-15
- 稿件说明：
移动端阅览
郁梅孔真真朱江英. 基于视觉阈值及通道融合的立体图像质量评价[J]. 光学精密工程, 2013,21(6): 1605-1612

YU Mei KONG Zhen-zhen ZHU Jiang-ying. Stereoscopic image quality Assessment based on visual threshold and channel fusion[J]. Editorial Office of Optics and Precision Engineering, 2013,21(6): 1605-1612
郁梅孔真真朱江英. 基于视觉阈值及通道融合的立体图像质量评价[J]. 光学精密工程, 2013,21(6): 1605-1612 DOI： 10.3788/OPE.20132106.1605.

YU Mei KONG Zhen-zhen ZHU Jiang-ying. Stereoscopic image quality Assessment based on visual threshold and channel fusion[J]. Editorial Office of Optics and Precision Engineering, 2013,21(6): 1605-1612 DOI： 10.3788/OPE.20132106.1605.

摘要

根据人眼对彩色图像不同颜色通道的敏感度不同，利用掩蔽效应对人眼感知立体图像质量产生的影响，提出了一种基于视觉阈值分析和通道融合的彩色图像客观质量评价方法。利用人眼视觉阈值确定立体图像的失真是否在人眼可察觉的范围，若失真程度小于视觉掩蔽阈值，则认为没有失真。利用原始和失真彩色图像RGB三通道各自左视点差值图和右视点差值图的奇异值与人眼视觉掩蔽阈值图的奇异值距离来衡量失真图像左右视点图像的质量。原始和失真图像对的绝对差图之差值图像和原始图像对的双目恰可察觉失真阈值图之间的奇异值距离被用于评价失真立体图像的深度感知好坏。不同失真类型下，左右视点质量融合以及左右视点评价和深度感知评价的融合其加权权值不同。对JPEG压缩、JPEG2000压缩、高斯白噪声、高斯模糊和H.264编码5种不同程度失真的312幅退化图像进行了测试，结果显示本文方法与主观感知有较好的一致性，总体CC (Pearson Linear Correlation Coefficient)达到0.94，总体SROCC （Spearman Rank Order Correlation Coefficient）达到0.94，整体均方根误差（RMSE）控制在5.9以内。

Abstract

According to the different sensitivities of human eyes for different color channels of color images and the effect of tolerable perception range of human eyes on color image perception，a color image objective quality assessment method based on visual threshold and channel integration is proposed. Visual threshold characteristics of human eyes are used to determine whether the distortion of a stereoscopic image can be perceived. If the degree of distortion is within the tolerable range of human eyes

the distortion is ignored. Singular values of difference maps between original and distorted images with respect to the left and right views are compared with singular values of the visual threshold map of original images

so as to assess the quality of the left and right views

respectively. For original and distorted stereoscopic images

the difference between their left view and the right view are calculated

and the difference map of the above two differences is further calculated. The singular values of the difference map are then compared with singular value of binocular just noticeable difference to assess the quality of stereo perception. For different types of distortion

the weights for fusing the assessments of the left and right views

and the weights for fusing the assessments of the left-right views and stereo perception are different. The experimental results on 312 stereoscopic images distorted with Gaussian blur

Gaussian white noise

JPEG

JP2K and H.264 show that the proposed objective model can achieve more than 0.94 Pearson Linear Correlation Coefficient(CC) and general Spearman Rank Order Correlation Coefficient(SROCC)

respectively

and the overall Rooted Mean Square Error(RMSE) is less than 5.9

which means that the assessment score obtained by the proposed model is well consistent with that obtained by human subjective perception.

关键词

Keywords

references

张艳, 安平, 张秋闻,等. 视觉关注度的立体图像质量评价[J].中国图像图形学报, 2012, 17(6):722-725. ZHANG Y, AN P, ZHANG Q W, et al.. Stereo image quality assessment based on visual attention [J]. Journal of Image and Graphics, 2012, 17(6): 722-725. (in Chinese)[2]ZILLY F, KLUGER J, KAUFF P. Production rules for stereo acquisition [J]. Proceedings of the IEEE, 2011, 99(4): 590-606.[3]SHAO F, JIANG GY, YU M, et al.. Asymmetric coding of multi-view video plus depth based 3-D video for view rendering [J]. IEEE Transactions on Multimedia, 2012, 14(1):157-167.[4]UREY H, CHELLAPPAN K V, ERDEN E, et al.. State of the art in stereoscopic and auto stereoscopic displays[J]. Proceedings of the IEEE, 2011, 99(4): 540-555.[5]范媛媛, 沈湘衡, 桑英军. 基于对比度敏感度的无参考图像清晰度评价[J]. 光学精密工程, 2011, 19(10):2485-2493. FAN Y Y, SHEN X H, SANG Y J. No reference image sharpness assessment based on contrast sensitivity [J]. Opt. Precision Eng., 2011, 19(10): 2485-2493. (in Chinese)[6]袁飞, 黄联芬, 姚彦. 基于视觉掩盖效应和奇异值分解的图像质量评测方法[J]. 光学精密工程, 2008, 16(4):706-713. YUAN F, HUANG L F, YAO Y, et al.. Study on auto focusing algorithm for automatic microscope [J]. Opt. Precision Eng., 2008, 16(4): 706-713. (in Chinese)[7]唐艳秋, 张星祥, 李新娥,等. 基于人眼视觉灰度识别特性的图像动态范围小波变换处理方法[J]. 液晶与显示, 2012, 27(3):385-390.TANG Y Q, ZHANG X X, LI X E,et al.. Image processing method of dynamic range with wavelet transform based on human visual gray recognition characteristics [J]. Chinese Journal of Liquid Crystals and Displays, 2012, 27(3):385-390. (in Chinese)[8]姚军财. 基于人眼对比度敏感视觉特性的图像质量评价方法[J]. 液晶与显示, 2011, 26(3):390-396.YAO C J.Image quality assessment method based on contrast sensitivity characteristics of human vision system [J]. Chinese Journal of Liquid Crystals and Displays, 2011, 26(3):390-396. (in Chinese)[9]沈丽丽, 侯春萍, 张卓筠,等. 基于三维特征和结构相似度的图像质量评价方法[J]. 光电子激光, 2010, 21(11):1713-1719. SHEN L L, HOU C P, ZHANG Z Y, et al.. A stereo image quality evaluation method based on three dimensional characteristics and structural similarity [J]. Journal of Optoelectronics Laser, 2010, 21(11): 1713-1719. (in Chinese)[10]SHAO H, CAO X, ER G H. Objective quality assessment of depth image based rendering in 3DTV system [C]. Proceedings of 3DTV Conference. Potsdam: IEEE Computer Society Press, 2009, 5069619: 1-4.[11]周俊明, 郁梅, 蒋刚毅,等. 利用奇异值分解法的立体图像客观质量评价模型[J]. 计算机辅助设计与图形学学报，2011, 23(5):870-877. ZHOU J M, YU M, JIANG G Y ,et al.. A singular value decomposition based objective quality assessment model on stereoscopic images [J]. Journal of Computer -Aided Design & Computer Graphics, 2011, 23(5):870-877.[12]SAZZAD Z, YAMAMAKA S, KAWAYOKE Y, et al.. Stereoscopic image quality prediction [C]. International Workshop on Quality of Multimedia Experience, San Diego, CA, 2009, 5246956:180-185. [13]YANG X K, LIN W S, LU ZH K, et al.. Motion-compensated residue preprocessing in video coding based on just noticeable distortion profile [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2005, 15(6):742-752.[14]汪源源, 孙志民, 蔡铮. 改进的奇异值分解法估计图像点扩散函数[J]. 光学精密工程, 2006,14(3):520-525. WANG Y Y, SUN Z M, CAI Z. Estimation of PSF of image system using modified SVD method [J]. Opt. Precision Eng., 2006, 14(3):520-525. (in Chinese)[15]杨嘉琛, 候春萍, 雷建军. 基于人眼视觉特征的立体图像质量客观评价方法[J].天津大学学报, 2009, 42(7):622-627. YANG J C, HOU C P, LEI J J. Objective quality evaluation method of stereo image based on human visual characteristics [J]. Journal of Tianjin University, 2009, 42(7):622-627. (in Chinese)[16]ZHAO Y, CHEN Z Z, ZHU C, et al.. Binocular just-noticeable-difference model for stereoscopic images [J]. IEEE Transactions on Signal Processing Letters, 2011, 18(1):19-22.[17]ZHOU J M, JIANG G Y, MAO X Y,et al.. Subjective quality analyses of stereoscopic images in 3DTV system[C]. Visual Communications and Image Processing Conference (VCIP2011), 2011:1-4.[18]BRUNNSTROM K, HANDS D, SPERANZA F, et al.. VQEG validation and ITU standardization of objective perceptual video quality metrics standards in a nutshell [J]. IEEE Transactions on Signal Processing Magazine, 2009, 26(3): 96-101.[19]顾珊波，邵枫，蒋刚毅,等. 基于支持向量回归的立体图像客观质量评价模型[J].电子与信息学报, 2012, 34(2):368-374. GU S, SHAO F, JIANG G Y, et al.. Objective stereoscopic image quality assessment model based on support vector regression [J]. Journal of Electronics & Information Technology, 2012, 34(2):368-374. (in Chinese) [20]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.[21]CHOU C H, CHEN C W. A perceptually optimized 3-D sub band codec for video communication over wireless channels [J]. IEEE Transactions on Circuits and Systems for Video Technology, 1996, 6(2):143-156.

浏览量

1100

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于局部方差和互信息的融合图像质量评价

基于纹理奇异值分解的全参考图像质量评价

基于断裂面邻域特征的文物碎片拼接

面向特大型齿轮的激光跟踪多站位定位