摘要
全面综述了超分辨图像质量评价的研究进展。超分辨图像质量评价是以人眼的主观质量评价结果为依据,利用算法模型对重建的超分辨图像进行评价。该评价方法对超分辨重建算法的优化和模型参数的选择具有重要的指导意义。首先对超分辨图像的主观评价方法进行阐述;其次对现有超分辨图像客观评价方法按照全参考型、部分参考型和无参考型进行了分类阐述,特别详细介绍了几种具有代表性的无参考质量评价的主要思想;接着从定量和定性两方面分别介绍了评价超分辨图像质量评价方法有效性的指标,并对评价算法的主要实验方法进行了简要阐述;最后对超分辨图像质量评价方法未来的发展趋势进行了展望。
This paper comprehensively surveys the development of Super-Resolution Image Quality Assessment(SRIQA).The objective of SRIQA is to design a computational model to measure the perceptual quality of Super-Resolution(SR)images based on the statistical results of subjective quality assessment. The SRIQA methods are significantly instructive for the optimization and the parameters selection of SR algorithms. First, this paper presents the subjective evaluation method for SR images. Next according to the categories of Full-Reference(FR), Reduced-Reference(RR), and No-Reference(NR)quality assessment methods, the existing objective quality assessment methods for SR images are introduced,respectively. Particularly, the major idea of NR quality assessment algorithms is presented in detail. Then the quantitative and qualitative evaluation indexes for SRIQA methods are provided, and the main experimental approaches for evaluating the effectiveness of the SR algorithms are described. Finally, the development trends of SRIQA are summarized.
引文
[1]曾凯,丁世飞.图像超分辨率重建的研究进展[J].计算机工程与应用,2017,53(16):29-35.
[2]Zhang K B,Tao D C,Gao X B,et al.Coarse-to-fine learning for single-image super-resolution[J].IEEE Transactions on Neural Networks and Learning Systems,2017,28(5):1109-1122.
[3]李云红,王珍,张凯兵,等.基于学习的图像超分辨重建方法综述[J].计算机工程与应用,2018,54(15):13-21.
[4]Zhang K B,Tao D C,Gao X B,et al.Learning multiple linear mappings for efficient single image super-resolution[J].IEEE Transactions on Image Processing,2015,24(3):846-861.
[5]Zhang K B,Gao X B,Tao D C,et al.Single image superresolution with non-local means and steering kernel regression[J].Image,2012,11:12.
[6]Xu Q Q,Jiang T T,Yao Y,et al.Random partial paired comparison for subjective video quality assessment via Hodge-Rank[C]//Proceedings of the 19th ACM International Conference on Multimedia,2011:393-402.
[7]蒋刚毅,黄大江,王旭,等.图像质量评价方法研究进展[J].电子与信息学报,2010,32(1):219-226.
[8]何南南,解凯,李桐,等.图像质量评价综述[J].北京印刷学院学报,2017,25(2):47-50.
[9]Ahmad T,Quershi S S.The full reference quality assessment metrics for super resolution of an image:shedding light or casting shadows?[C]//International Conference on Electronics and Information Engineering,2010,2:224-227.
[10]Ye X,Lu X Q.A performance evaluation of image interpolation and super-resolution algorithms[C]//International Conference on Multimedia Technology,2011:4776-4779.
[11]Luke?T,Fliegel K,Klíma M.Performance evaluation of image quality metrics with respect to their use for super-resolution enhancement[C]//IEEE the 5th International Conference on Quality of Multimedia Experience,2013:42-43.
[12]王志明.无参考图像质量评价综述[J].自动化学报,2015,41(6):1062-1079.
[13]Luke?T,Fliegel K,Klima M.Objective image quality assessment of multiframe super-resolution methods[C]//IEEE 23rd International Conference on Radioelektronika,2013:267-272.
[14]Sheikh H R,Wang Z,Cormack L,et al.LIVE image quality assessment database release2[EB/OL].(2015-02-04).[2018-10-16].http://live.ece.utexas.edu/research/quality.
[15]Ponomarenko N,Lukin V,Zelensky A,et al.TID2008-a database for evaluation of full reference visual quality assessment metrics[J].Advances of Modern Radio Electronics,2009,10(4):30-45.
[16]Ponomarenko N,Jin L,Ieremeiev O,et al.Image database TID2013:peculiarities,results and perspectives[J].Signal Processing Image Communication,2015,30:57-77.
[17]Fowlkes C,Martin D,Malik J.The Berkeley segmentation dataset and benchmark(BSDB)[EB/OL].[2018-10-16].http://www.cs.berkeley.edu/projects/vision/grouping/segbench.
[18]Yang C Y,Ma C,Yang M H.Single-image super-resolution:a benchmark[C]//European Conference on Computer Vision.Cham:Springer,2014:372-386.
[19]Ma C,Yang C Y,Yang X,et al.Learning a no-reference quality metric for single-image super-resolution[J].Computer Vision and Image Understanding,2017,158:1-16.
[20]Wang G,Li L,Li Q,et al.Perceptual evaluation of singleimage super-resolution reconstruction[C]//IEEE International Conference on Image Processing,2017:3145-3149.
[21]Methodology for the subjective assessment of the quality of television pictures:ITU-R BT.500-13[R].Geneva,Switzerland:International Telecommunication Union,2013.
[22]He L H,Gao F,Hou W L,et al.Objective image quality assessment:a survey[J].International Journal of Computer Mathematics,2014,91(11):2374-2388.
[23]Zhang Y Q,Liu J Y,Yang W H,et al.Image super-resolution based on structure-modulated sparse representation[J].IEEE Transactions on Image Processing,2015,24(9):2797-2810.
[24]刘薇,钱慧芳.单帧学习与多帧重建结合的超分辨率盲重建方法[J].西安工程大学学报,2014,28(5):588-592.
[25]于康龙,秦卫城,杨进,等.超分辨重建图像质量评价算法[J].计算机工程与应用,2017,53(2):201-205.
[26]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.
[27]Kim Y J,Park J H,Shin G S,et al.Evaluating super resolution algorithms[C]//Image Quality and System Performance VIII.International Society for Optics and Photonics,2011:78670D.
[28]Sheikh H R,Bovik A C.Image information and visual quality[J].IEEE Transactions on Image Processing,2006,15(2):430-444.
[29]Sheikh H R,Bovik A C,De Veciana G.An information fidelity criterion for image quality assessment using natural scene statistics[J].IEEE Transactions on Image Processing,2005,14(12):2117-2128.
[30]Kim W H,Lee J S.Framework for fair objective performance evaluation of single-image super-resolution algorithms[J].Electronics Letters,2015,51(1):42-44.
[31]Liu Z,Laganière R.Phase congruence measurement for image similarity assessment[J].Pattern Recognition Letters,2007,28(1):166-172.
[32]Zhang L,Zhang L,Mou X,et al.FSIM:a feature similarity index for image quality assessment[J].IEEE Transactions on Image Processing,2011,20(8):2378-2386.
[33]Zhang J,Huang C L,Fan X Q.On evaluation criterion of image super-resolution reconstruction[C]//IEEE the2nd International Conference on Innovative Computing,Information and Control,2007:576.
[34]Foroosh H,Zerubia J B,Berthod M.Extension of phase correlation to sub-pixel registration[J].IEEE Transactions on Image Processing,2002,11(3):188-200.
[35]Nelson K,Bhatti A,Nahavandi S.Performance evaluation of multi-frame super-resolution algorithms[C]//International Conference on Digital Image Computing Techniques and Applications,2012:1-8.
[36]Tian L,Suzuki A,Koike H.Task-oriented evaluation of super-resolution techniques[C]//IEEE 20th International Conference on Pattern Recognition,2010:493-498.
[37]Wang Z,Bovik A C.Modern image quality assessment[J].Synthesis Lectures on Image,Video,and Multimedia Processing,2006,2(1):1-156.
[38]Yu K L,Meng Z K,Sun M J.Image quality assessment:a reduced reference algorithm for the super-resolution reconstruction image[C]//IEEE the 3rd International Conference on Instrumentation,Measurement,Computer,Communication and Control,2013:171-175.
[39]张振东,陈健,王伟国,等.基于SSIM_NCCDFT的超分辨率复原评价方法研究[J].液晶与显示,2015,30(4):713-721.
[40]He Y Q,Chen S,Wei J G.Assessment method of image super resolution reconstruction based on local similarity[C]//International Conference on Internet Multimedia Computing and Service,2013:154-157.
[41]Fang Y M,Liu J Y,Zhang Y B,et al.Quality assessment for image super-resolution based on energy change and texture variation[C]//IEEE International Conference on Image Processing,2016:2057-2061.
[42]Shan Q,Li Z,Jia J,et al.Fast image/video upsampling[J].ACM Transactions on Graphics,2008,27(5):153.
[43]Glasner D,Bagon S,Irani M.Super-resolution from a single image[C]//IEEE the 12th International Conference on Computer Vision,2009:349-356.
[44]Yang J,Lin Z,Cohen S.Fast image super-resolution based on in-place example regression[C]//IEEE Conference on Computer Vision and Pattern Recognition,2013:1059-1066.
[45]Kang L,Ye P,Li Y,et al.Convolutional neural networks for no-reference image quality assessment[C]//IEEE Conference on Computer Vision and Pattern Recognition,2014:1733-1740.
[46]Dong W S,Zhang L,Shi G M,et al.Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization[J].IEEE Transactions on Image Processing,2011,20(7):1838-1857.
[47]Yeganeh H,Rostami M,Wang Z.Objective image quality assessment of multiframe super-resolution:a natural scene statistics approach[C]//IEEE International Conference on Image Processing,2012:1481-1484.
[48]Zhang W,Fan Z C.A no-reference contourlet-decomposition-based image quality assessment method for superresolution reconstruction[C]//SPIE/COS Photonics Asia International Society for Optics and Photonics,2014,9273:927326.
[49]黄慧娟,禹晶,孙卫东.基于SVD的超分辨率重建图像质量无参考评价方法[J].计算机辅助设计与图形学学报,2012,24(9):1204-1210.
[50]Fang Y M,Zhang C,Yang W H,et al.Blind visual quality assessment for image super-resolution by convolutional neural network[J].Multimedia Tools and Applications,2018,77(22):29829-29846.
[51]Williams S.Pearson’s correlation coefficient[J].New Zealand Medical Journal,1996,109(1015):38.
[52]Sheikh H R,Sabir M F,Bovik A C.A statistical evaluation of recent full reference image quality assessment algorithms[J].IEEE Transactions on Image Processing,2006,15(11):3440-3451.
[53]Sheskin D J.Spearman’s rank-order correlation coefficient[M].Handbook of parametric and nonparametric statistical procedures.[S.l.]:CRC Press,2007:1353-1370.
[54]Abdi H.The Kendall rank correlation coefficient[M]//Encyclopedia of measurement and statistics.Thousand Oaks:Sage Publications,2007:508-510.
