基于IGM和深度感知的立体图像质量评价

doi:10.12066/j.issn.1007-2861.1964

上海大学学报(自然科学版) ›› 2019, Vol. 25 ›› Issue (5): 692-700.doi: 10.12066/j.issn.1007-2861.1964

基于IGM和深度感知的立体图像质量评价

朱芸, 王永芳(), 帅源

上海大学通信与信息工程学院, 上海 200444

收稿日期:2017-06-14 出版日期:2019-10-30 发布日期:2019-10-31
通讯作者: 王永芳 E-mail:yfw@shu.edu.cn
基金资助:
国家自然科学基金资助项目(61671283);国家自然科学基金资助项目(61301113);上海市自然科学基金资助项目(13ZR14165)

Reduced-reference quality assessment of stereoscopic images based on IGM and depth perception

Yun ZHU, Yongfang WANG(), Yuan SHUAI

School of Communication and Information Engineering,Shanghai University, Shanghai 200444, China

Received:2017-06-14 Online:2019-10-30 Published:2019-10-31
Contact: Yongfang WANG E-mail:yfw@shu.edu.cn

摘要/Abstract

摘要：

根据人类视觉系统的特点, 提出了一种基于内在推理机制(internal generative mecha-nism, IGM)和深度感知的半参考立体图像质量评价(stereoscopic image quality assessment, SIQA)方法, 用图像质量和深度感知质量2个因素来评估立体图像的体验质量(quality of experience, QoE). 首先, 对于图像质量, 根据大脑的内在推理机制将左右视点分别分解成可预测部分和不确定部分, 用基于灰度共生矩阵(gray level co-occurrence matrices, GLCM)和基于视觉信息量的质量评价方法计算这2个部分的质量; 然后, 对于深度感知质量, 采用一种改进的自然场景统计(natural scene statistics, NSS)模型来预测这部分质量; 最后, 将图像质量和深度感知质量融合为立体图像体验质量. 实验结果表明, 该算法在常用视频库上的结果优于现有的评价方法, 且与主观感知具有较高一致性.

关键词: 立体图像质量评价, 内在推理机制, 灰度共生矩阵, 视觉信息量, 自然场景统计

Abstract:

In this paper, a reduced reference stereoscopic image quality assessment (SIQA) method is proposed based on the internal generative mechanism (IGM) and depth perception. The method determines 3D quality of experience (QoE) by focusing on image quality and depth perception quality. For image quality, a stereoscopic image is decomposed into a predicted portion and an uncertain portion according to IGM of the brain, handled with the metric based on gray level co-occurrence matrices (GLCM) and visual information separately. The depth perceptual quality is measured with an improved natural scene statistics (NSS) model. The image quality and depth perception quality are then integrated to obtain the overall quality. Experimental results show that the proposed metric outperforms the state-of-the-art metrics and is consistent to subjective ratings over widely used databases.

Key words: stereoscopic image quality assessment (SIQA), internal generative mechanism (IGM), gray level co-occurrence matrices (GLCM), visual information, natural scene statistics (NSS)

中图分类号:

TN919.82

朱芸, 王永芳, 帅源. 基于IGM和深度感知的立体图像质量评价[J]. 上海大学学报(自然科学版), 2019, 25(5): 692-700.

Yun ZHU, Yongfang WANG, Yuan SHUAI. Reduced-reference quality assessment of stereoscopic images based on IGM and depth perception[J]. Journal of Shanghai University（Natural Science Edition）, 2019, 25(5): 692-700.

图/表 5

参考文献 22

[1]	Yasakethu S L P, Hewage C T E R, Fernando W A C , et al. Quality analysis for 3D video using 2D video quality models[J]. IEEE Trans Consum Electron, 2008,54(4):1969-1976.
[2]	Wang J H, Zeng K, Wang Z . Quality prediction of asymmetrically distorted stereoscopic images from single views[C]// IEEE International Conference on Multimedia and Expo (ICME). 2014: 1-6.
[3]	Gu S B, Shao F, Jiang G Y . Objective stereo images quality assessment model based on support vector machine[J]. Journal of Electronics and Information, 2012,34(2):368-374.
[4]	You J Y, Xing L Y, Perkis A , et al. Perceptual quality assessment for stereoscopic images based on 2D image quality metrics and disparity analysis[C]// Proc Int Workshop Video Process Quality Metrics Consum Electron, Scottsdale, AZ, USA. 2010: 61-66.
[5]	Benoit A, le Callet P, Campisi P , et al. Quality assessment of stereoscopic images[J]. EURASIP J Image Video Process, 2009,2008:1-13.
[6]	Carnec M, le Callet P, Barba D . An image quality assessment method based on perception of structural information[C]// Proc IEEE Int Conf Image Process. 2003: 185-193.
[7]	Yang J C, Hou C P, Zhou Y , et al. Objective quality assessment method of stereoimages[C]// Proc 3DTV Conf True Vis.-Capture. 2009.
[8]	Shao F, Li K M, Lin W S , et al. Using binocular feature combination for blind quality assessment of stereoscopic images[J]. IEEE Signal Processing Letters, 2015,22(10):1548-1551.
[9]	Chen M J, Su C C, Kwon D K , et al. Full-reference quality assessment of stereopairs accounting for rivalry[J]. Image Commun, 2013,28(9):143-1155.
[10]	Bensalma R, Larabi M C . A perceptual metric for stereoscopic image quality assessment based on the binocular energy[J]. Multidimens Syst Signal Process, 2013,24(2):281-316.
[11]	Galkandage C, Calic J, Dogan S , et al. Stereoscopic video quality assessment using binocular energy[J]. IEEE Journal of Selected Topics in Signal Processing, 2017,11(1):102-112.
[12]	Wang J H, Abdul R, Zeng K , et al. Quality prediction of asymmetrically distorted stereoscopic 3D images[J]. IEEE Transactions on Image Processing, 2015,24(11):3400-3414.
[13]	Wu J J, Lin W S, Shi G M , et al. Perceptual quality metric with internal generativemechanism[J]. IEEE Transactions on Image Processing, 2013,22(1):43-54.
[14]	Li D D . Multi-scale GLCM based quantitative assessment method for ultrasound liver fibrosis images[C]// Signal Processing(ICSP) . 2016.
[15]	Frison K, Kilner J, Harrison L . A free energy principle for the brain[J]. J Physiology, 2006,100(1/2/3):70-87.
[16]	刘宝 . 基于双目视觉的 3D 图像质量评价[D]. 北京: 北京理工大学, 2016: 14-16.
[17]	Yang L P, Du H Q, Xu J T , et al. Blind image quality assessment on authentically distortion images with perceptual features[C]// Image Processing (ICIP). 2016: 2042-2046.
[18]	Zhu H, Yu M, Song Y , et al. A stereo video quality assessment method for compression distortion[C]// Computational Science and Computational Intelligence (CSCI). 2015.
[19]	Mokhtari A, Ribeiro A . RES: regularized stochastic BFGS algorithm[J]. IEEE Transactions on Signal Processing, 2014,23(62):6089-6104.
[20]	Wang J H, Zeng K, Zhou W . Quality prediction of asymmetrically distorted stereoscopic images from single views[C]// Multimedia and Expo (ICME). 2014.
[21]	Wang J H, Zeng K, Zhou W . Quality prediction of asymmetrically distorted stereoscopic 3D images[J]. IEEE Transactions on Image Processing, 2015,24(11):3400-3414.
[22]	Chen M J, Su C C, Kwon D K , et al. Full-reference quality assessment of stereopairs accounting for rivalry[J]. IEEE Transactions on Image Processing, 2013,22(9):3379-3391.

基于IGM和深度感知的立体图像质量评价

Reduced-reference quality assessment of stereoscopic images based on IGM and depth perception

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 22

相关文章 0

编辑推荐

Metrics

本文评价