彩色图像的RGB(红绿蓝)3个通道间具有密切的相关性,在RGB空间中进行超分辨率操作容易破坏这种相关性,会导致色彩伪影.然而在lαβ彩色空间中,3个通道之间的相关性很小.本文借鉴空间转换的思想,提出了一种将彩色图像转化到lαβ空间进行超分辨率的方法,在3个通道单独进行超分辨率处理.实验结果证明了该方法对RGB 3个通道的相关性破坏极小.
Three channels of color image have a close correlation.Super resolution in the RGB space is easy to break the relevance and cause artifacts.However,there is a little relevance between three channels in the lαβ color space.In this paper,a new approach to achieve color image super resolution is presented,which used the concept of space conversion. Super resolution is performed separately in the lαβ channels.The experimental results demonstrate that the approach is effective and will minimally break the relevance between the color channels.
[1] SHAH N R.,ZAKHORB A.Resolution enhancement of color video sequences[J].IEEE Transactions on Image Processing,1999,8(6):879 - 885.DOI:10.1109/83.766865.
[2] TOM B C,KATSAGGELOS A K.Resolution enhancement of monochrome and color video using motion compensation[J].IEEE Transactions on Image Processing,2001,10(2):278 - 287.DOI:10.1109/83.902292.
[3] TIMOFTE R D V,GOOL L V.Anchored neighborhood regression for fast example-based superresolution[Z].IEEE International Conference on Computer Vision,Sydney,Australia,2013.DOI:10.1109/ICCV.2013.241.
[4] LI J M,QU Y,LI C H,et al.Image super-resolution base on multi-kernel regression[J].International Journal of Multimedia Tools and Applications,2016,75:4115-4128.DOI:10.1007/s11042-015-3016-4.
[5] YEGANLI F,NAZZAL M,UNAL M,et al.Image super-resolution via sparse representation over multiple learned dictionaries based on edge sharpness[J].International Journal of Signal,Image and Video Processing,2016,10:535-542.DOI:10.1007/s11760-015-0771-7.
[6] HOU H S,ANDREWSS H.Cubic splines for image interpolation and digital filtering[J].IEEE Transactions on Acoust Speech Signal Process,1978,26:508-517.DOI:10.1109/TASSP.1978.1163154.
[7] IRANI M,PELEG S.Improving resolution by image registration[J].International Journal of Graph Models Image Process,1991,53:231-239.DOI:10.1016/1049-9652(91)90045-L.
[8] YANG J,WRIGHT J,HUANG T,et al.Image super-resolution via sparse representation[J].IEEE Transactions on Image Processing,2010,19:2861-2873.DOI:10.1109/TIP.2010.2050625.
[9] SUN J,ZHENG N,TAO H,et al.Image hallucination with primal sketch priors[Z].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,Madison,Wisconsin,2003.DOI:10.1109/CVPR.2003.1211539.
[10] TAI Y W,TONG W S,TANG C K.Perceptually-inspired and edge-directed color image super-resolution[Z].IEEE Computer Society Conference on Computer Vision and Pattern Recognition,New York,USA,2006.DOI:10.1109/CVPR.2006.221.
[11] PARK S C,PARK M K,KANG M G.Super-resolution image reconstruction:a technical review[J].IEEE Transactions on Signal Processing,2003,5:21-36.DOI:10.1109/MSP.2003.1203207.
[12] 沈红斌,杨杰,刘小军,等,基于模糊信息增益的图像相关性度量[J].上海交通大学学报,2006,40(3):466-470. SHEN H B,YANG J,LIU X J,et al.New image correlation analysis based on fuzzy information gain[J].Journal of Shanghai Jiaotong University.2006,40(3):466-470.
[13] 曹文伦,彭国华,秦洪元,等,利用色彩分量相关性的彩色图像分形编码方法[J].计算机工程与应用,2004,40(22):51-55. CAO W L,PENG G H,QIN H Y,et al.Color image fractal coding method using color component correlation[J].Computer Engineering and Applications.2004,40(22):51-55.
[14] RUDERMAN D L,CRONIN T W,CHIAO C C.Statistics of cone responses to natural images:implications for visual coding[J].Journal of the Optical Society of America A,1998,15(8):2036-2045.DOI:10.1364/JOSAA.15.002036.
[15] ZHAO S B,HAN H,PENG S L.Wavelet-domain HMT-based image super-resolution[Z].International Conference on Image Processing,Barcelona,Catalonia,Spain,2003.DOI:10.1109/ICIP.2003.1246841.
