[1]姜峰,郭美思,刘绍辉,等.基于感知视觉重要性的立体图像质量评价[J].智能系统学报,2012,7(5):414-422.
JIANG Feng,GUO Meisi,LIU Shaohui,et al.Quality assessment of stereoscopic images based on the significance of perceptual vision[J].CAAI Transactions on Intelligent Systems,2012,7(5):414-422.
点击复制
JIANG Feng,GUO Meisi,LIU Shaohui,et al.Quality assessment of stereoscopic images based on the significance of perceptual vision[J].CAAI Transactions on Intelligent Systems,2012,7(5):414-422.
基于感知视觉重要性的立体图像质量评价
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
7
期数:
2012年第5期
页码:
414-422
栏目:
学术论文—机器感知与模式识别
出版日期:
2012-10-25
- Title:
- Quality assessment of stereoscopic images based on the significance of perceptual vision
- 文章编号:
- 1673-4785(2012)05-0414-09
- Keywords:
- image quality assessment; stereoscopic image; just noticeable distortion(JND); visual psychology; physiological model; perceptual vision
- 分类号:
- TP391
- 文献标志码:
- A
- 摘要:
- 视觉心理、生理因素是有效、准确评价图像质量的重要依据.尽管在计算层面已有众多视觉心理、生理计算模型及方法为其提供支持，但在图像质量评价任务中如何分析各种孤立方法之间的内在关系进而使之有效协同，是使得评价结果更符合人主观评测的关键.从图像质量评价的角度出发，功能上将人眼的视觉注意区域定义并数学形式化为视觉初期注意区域与视觉转移期的劣质区域；同时考虑人眼的感知冗余特性，结合JND感知冗余模型，进而提出了图像质量评价范畴下的视觉感知模型PVSSIM.以此为依据，将感知视觉的方法在二维图像数据库中验证其可行性，并将其引入到立体图像质量评价中.实验结果表明，提出的客观评价方法与传统方法相比，充分考虑到了图像质量评价任务中各种视觉心理、生理因素的协同，与人主观的图像质量评价相比具有更高的相关度，评价方法在立体图像库中能很好地与主观评价相吻合，达到了预期的效果.
- Abstract:
- The visual psychological and physiological factors are crucial for the assessment on image quality. There are many visual, psychological and physiological calculation models used to support the assessment of image quality, however, how to analyze the intrinsic relations among various isolated methods and further effectively coordinate them in the task of image quality assessment is the key to making the assessment results more conform to subjective assessment of human. The definition and formalization of visual attention areas as saliency in the early vision period and poorquality area for vision transformation periods were examined from an image quality angle. Simultaneously, the property of perceptual redundancy of human eyes, JND(just noticeable distortion) perception redundancy model, and vision perception model PVSSIM of image equality assessment will be examined. Based on the research findings, feasibility of vision perception methods are verified using a twodimensional image database study through the introduction of image stereoscopic. The experimental results confirm that, in comparison with traditional methods, the raised objective assessment method sufficiently considers the coordination of various psychological and physiological factors in the task of image quality assessment, it is more relevant to the subjective image quality assessment of human. In the stereoscopic image database, the assessment method may properly coincide with the subjective assessment, the expectable effect is realized.
- 参考文献/References:
-
［1］LIPTON L. Foundations of the stereoscopic cinema: a study in depth［M］. New York, USA: Van Nostrand Reinhold, 1982.
［2］YEMEZ Y, GUDUKBAY U, ZABULIS X, et al. Scene representation technologies for 3DTV: a survey［J］. IEEE Transactions on Circuits and Systems for Video Technology, 2007, 17(11): 15871605.
［3］丁剑飞,刘永进.三维立体显示技术综述［J］.系统仿真学报, 2008, 20(S1): 132135.
DING Jianfei, LIU Yongjin. A survey on threedimension display technologies［J］. Journal of System Simulation, 2008, 20(Suppl.1): 132135.
［4］SAKAMOTO K, KIMURA R, TAKAKI M. Parallax polarizer barrier stereoscopic 3D display systems［C］//Proceedings of the 2005 International Conference on Active Media Technology. Kagawa, Japan, 2005: 469474.
［5］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): 600612.
［6］WANG Z, SIMONCELLI E P, BOVIK A C. Multiscale structural similarity for image quality assessment［C］//Proceedings of the 37th IEEE Asilomar Conference on Signals, Systems and Computers. Pacific Grove, USA, 2003: 13981402.
［7］MOORTHY A K, BOVIK A C. Visual importance pooling for image quality assessment［J］. IEEE Journal of Selected Topics in Signal Processing, Special Issue on Visual Media Quality Assessment, 2009, 3(2): 193201.
［8］WANG Zhou, LI Qiang. Information content weighting for perceptual image quality assessment［J］. IEEE Transactions on Image Processing, 2011, 20(5): 11851198.
［9］GUO An′an, ZHAO Debin, LIU Shaohui, et al. Visual attention based image quality assessment［C］//18th IEEE International Conference on Image Processing. Brussels, Belgium, 2011: 32973300.
［10］YOU Junyong, XING Liyuan, PERKIS A, et al. Perceptual quality assessment for stereoscopic images based on 2D image quality metrics and disparity analysis［C］//Fifth International Workshop on Video Processing and Quality Metrics for Consumer Electronics. Scottsdale, USA, 2010: 40334036.
［11］YANG Jiachen, HOU Chunping, ZHOU Yuan, et al. Objective quality assessment method of stereo images［C］//3DTVConference: The True Vision Capture, Transmission and Display of 3D Video. Potsdam, Germany, 2009: 14.
［12］HEWAGE C T E R, MARTINI M G. Reducedreference quality metric for 3D depth map transmission［C］//3DTVConference: The True Vision Capture, Transmission and Display of 3D Video. Tampere, Finland, 2010: 14.
［13］XING Liyuan, YOU Junyong, EBRAHIMI T, et al. A perceptual quality metric for stereoscopic crosstalk perception［C］//17th IEEE International Conference on Image Processing. Hong Kong, China, 2010: 40334036.
［14］ROUSHAIN A, SAZZAD P, HORITA Z M, et al. No reference stereoscopic image quality assessment［C］//Proceedings of the SPIE Volume 7524: Stereoscopic Displays and Applications XXI. San Jose, USA, 2010: 1721.
［15］KIM D H, MIN D B, OH J H, et al. Depth map quality metric for threedimensional video［C］//Proceedings of the SPIE Volume 7237: Stereoscopic Displays and Applications XX. San Jose, USA, 2009: 2934.
［16］OLSSON R, SJOSTROM M. A depth dependent quality metric for evaluation of coded integral imaging based 3Dimages［C］//3DTVConference: The True Vision Capture, Transmission and Display of 3D Video. Kos, Greece, 2007: 14.
［17］TAKAHASHI K, NAEMURA T. Unstructured light field rendering using onthefiy focus measurements［C］//IEEE International Conference on Multimedia and Expo. Amsterdam, The Netherlands, 2005: 205208.
［18］王翔.数字图像缩放及图像质量评价关键技术研究［D］.杭州:浙江大学, 2012: 105126. WANG Xiang. Research on image scaling and image quality assessment［D］. Hangzhou: Zhejiang University, 2012: 105126.
［19］张桦.基于视觉感知的图像质量评价方法研究［D］.杭州:浙江大学, 2009: 6888.
ZHANG Ye. Research on image quality assessment based on visual perception［D］. Hangzhou: Zhejiang University, 2009: 6888.
［20］王科俊,刘靖宇,马慧,等.手指静脉图像质量评价［J］.智能系统学报, 2011, 6(4): 324327.
WANG Kejun, LIU Jingyu, MA Hui, et al. A finger vein image quality assessment method［J］. CAAI Transactions on Intelligent Systems, 2011, 6(4): 324327.
［21］CHOU Chunhsien, LI Yunchin. A perceptually tuned subband image coder based on the measure of justnoticeabledistortion profile［J］. IEEE Transactions on Circuits and Systems for Video Technology, 1995, 5(6): 467476.
［22］HOU Xiaodi, ZHANG Liqing. Saliency detection: a spectral residual approach［C］//IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis, USA, 2007: 18.
［23］SHEIKH H R, SESHADRINATHAN K, MOORTHY A K, et al. Image and video quality assessment research at LIVE［EB/OL］. (20120312)［20120615］. http://live.ece.utexas.edu/research/quality/.
- 相似文献/References:
-
[1]王科俊,刘靖宇,马慧,等.手指静脉图像质量评价[J].智能系统学报,2011,6(4):324.
WANG Kejun,LIU Jingyu,MA Hui,et al.A finger vein image quality assessment method[J].CAAI Transactions on Intelligent Systems,2011,6():324.
[2]王伟,刘辉,杨俊安.一种特征字典映射的图像盲评价方法研究[J].智能系统学报,2018,13(6):989.[doi:10.11992/tis.201805027]
WANG Wei,LIU Hui,YANG Junan.Blind quality evaluation with image features codebook mapping[J].CAAI Transactions on Intelligent Systems,2018,13():989.[doi:10.11992/tis.201805027]
[3]严浙平,曲思瑜,邢文.水下图像增强方法研究综述[J].智能系统学报,2022,17(5):860.[doi:10.11992/tis.202108022]
YAN Zheping,QU Siyu,XING Wen.An overview of underwater image enhancement methods[J].CAAI Transactions on Intelligent Systems,2022,17():860.[doi:10.11992/tis.202108022]
备注/Memo
收稿日期： 2012-06-18.
网络出版日期：2012-09-21.
基金项目：国家自然科学基金资助项目（61100096）；国家“973”计划资助项目（2009CB320905）.
通信作者：姜峰.
E-mail: fjiang@hit.edu.cn.
作者简介：
姜峰，男，1978年生，副教授，硕士生导师，博士，主要研究方向为计算机视觉、模式识别、视频编码，发表学术论文60余篇.
郭美思，女，1987年生，硕士研究生，主要研究方向计算机视觉、视频编码.
刘绍辉，男，1977年生，副教授，硕士生导师，博士，主要研究方向为计算机视觉、视频编解码，发表学术论文60余篇.
赵德斌，男，1963年生，教授，博士生导师，主要研究方向为视频编码、图像处理和视频传输.作为负责人完成和在研国家“973计划”项目、国家“863”计划项目、国家自然科学基金重点项目与面上项目、国际合作项目等科研项目19项.共获得国家及省部级奖励13项，其中国家技术发明二等奖1项，国家科学技术进步二等奖2项，省部级科学技术进步一、二、三等奖共10项，发明专利14项.发表学术论文270余篇，其中被SCI检索62篇、EI检索202篇.
更新日期/Last Update:
2012-11-13