期刊文献+

基于字典学习与稀疏表示的灰度图像颜色重建算法 被引量:8

Color Reconstruction Algorithm for Grayscale Images Based on Dictionary Learning and Sparse Representation
下载PDF
导出
摘要 为了充分利用参考彩色图像与待处理灰度图像的关联关系,进一步提高图像颜色重建的自动化程度,利用稀疏表示理论和字典学习方法,提出一种自动全局图像着色算法.首先利用图像亮度、特征信息、图像颜色信息之间的相关性,依据参考图像训练出一个亮度-特征-颜色的联合字典;然后利用目标灰度图像的亮度和特征信息计算出其在该字典下的稀疏表示系数;最后利用上述联合字典与计算得到的稀疏表示系数进行灰度图像的颜色信息重建.文中算法无需进行图像分割,针对整幅图像进行着色,是一种自动的全局算法.实验结果表明,该算法可以有效地对灰度图像进行着色,对于色调单一的图像,着色效果更好. In order to take full advantage of the relationship between reference color images and the objective grayscale image and to improve the degree of automation for image color reconstruction, we presented an automatic algorithm for image colorization based on dictionary learning and sparse representation. Firstly, a joint dictionary is trained by reference color images according to the correlations among the luminance, feature and color of trained images. And then the sparse coefficients under the joint dictionary for the objective grayscale image are computed by using its luminance and feature information. Finally, the color information is reconstructed using the above joint dictionary and the obtained sparse coefficients. Image segmentation is not necessary in the proposed algorithm. The color reconstruction is made on the entire image and therefore the proposed algorithm is global and automatic. Experimental results demonstrate that the algorithm presented in this paper is effective and efficient, espec
出处 《计算机辅助设计与图形学学报》 EI CSCD 北大核心 2014年第7期1092-1098,1108,共8页 Journal of Computer-Aided Design & Computer Graphics
基金 国家自然科学基金(61073079 61272028) 中央高校基本科研业务费专项基金(2013JBZ003) 高等学校博士点基金(20120009110008) 教育部新世纪优秀人才支持计划(NCET-12-0768) 教育部创新团队发展计划(IRT201206)
关键词 图像处理 颜色重建 稀疏表示 字典学习 压缩感知 image processing color reconstruction sparse representation dictionary learning compressive sensing
  • 相关文献

参考文献15

  • 1Chang Y H,Saito S,Nakajima M.Example-based color transformation of image and video using basic color categories[J].IEEE Transactions on Image Processing,2007,16(2):329-336.
  • 2Levin A,Lischinski D,Weiss Y.Colorization using optimization [C]//Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH.New York:ACM Press,2004:689-694.
  • 3Yatziv I.,Sapiro G.Fast image and video colorization using chrominanee blending [J].IEEE Transactions on Image Processing,2006,15(5):1120-1129.
  • 4Welsh T,Ashikhmin M,Mueller K.Transferring color to greyscale images [C]//Computer Graphics Proceedings,Annual Conference Series,ACM SIGGRAPH.New York:ACM Press,2002:277-280.
  • 5Donoho D L.Compressed sensing [J].IEEE Transactions on Information Theory,2006,52(4):1289-1306.
  • 6Elad M,Figueiredo M A T,Yi M.On the role of sparse and redundant representations in image processing [J].Proceedings of the IEEE,2010,98(6):972-982.
  • 7Elad M,Aharon M.Image denoising via learned dictionaries and sparse representation [C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2006 895-900.
  • 8Mairal J,Elad M,Sapiro G.Sparse representation for color image restoration [J].IEEE Transactions on hnage Processing,2008,17(1):53-69.
  • 9Xu Z B,Sun J.Image inpainting by patch propagation using patch sparsity [J].IEEE Transactions on Image Processing,2010,19(5):1153-1165.
  • 10Yang J C,Wright J,Huang T S,et al.Image super-resolution via spatse representation [J].IEEE Transaction on Image Processing,2010,19(11):2861-2873.

二级参考文献12

  • 1Levin A, Lischinski D, Weiss Y. Colorization using optimization [C] //Computer Graphics Proceedings, Annual Conference Series, ACM SIGGRAPH. New York: ACM Press, 2004:689-594.
  • 2Yatziv L, Sapiro G. Fast image and video colorization using chrominance blending [J]. IEEE Transactions on Image Processing, 2006, 15(5)= 1120-1129.
  • 3Qu Y G, Wong T T, Heng P A. Manga eolorization [C] // Computer Graphics Proceedings, Annual Conference Series, ACM SIGGRAPH. New York: ACM Press, 2006 : 1214-1220.
  • 4Welsh T, Ashikhmln M, Mueller K. Transferring color to greyscale images [C] //Computer Graphics Proceedings, Annual Conference Series, ACM SIGGRAPH. New York: ACM Press, 2002:277-280.
  • 5Irony R, Cohen-Or D, Lischinski D. Colorization by example [C] //Proceedings of Eurographics Symposium on Rendering. Aire-la-Ville: Eurographics Association Press, 2005: 201- 210.
  • 6Elad M, Aharon M. Image denoising via learned dictionaries and sparse representation [C] //Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2006:895-900.
  • 7Mairal J, Elad M, Sapiro G. Sparse representation for color image restoration [J]. IEEE Transactions on Image Processing, 2008, 17(1) ~ 53-69.
  • 8Wang J J, Yang J C, Yu K, etal. Locality-constrained linear coding for image classification [C] //Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE Computer Society Press, 2010:3360-3367.
  • 9Aharon M, Hlad M, t3ruckstein A. K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation [J]. IEEE Transactions on Signal Processing, 2006, 54(11) 4311-4322.
  • 10Pati Y C, Rezaiifar R, Krishnaprasad P S. Orthogonal matching pursuit : recurslve function approximation with applications to wavelet decomposition [C]//Proceedings of the 27th Asilomar Conference on Signals, Systems, and Computers. Los Alamitos: IEEE Computer Society Press, 1993, 1:40-44.

共引文献2

同被引文献40

  • 1LIRON Y, GUILLERMO S. Fast image and videocolorization using chrominance blending [J]. IEEETranscations on Image Processing, 2006, 15(5): 1120-1129.
  • 2HORIUCHI T. Estimation of color for gray-levelImage byprobabilistic relaxation[C] 椅ICPR 2002 Proceedings ofthe 16th International Conference on Pattern Recogni-tion Washington, DC: IEEE Computer Socitey, 2002: 867-870.
  • 3LEVIN A, LISCHINSKI D, WEISS Y. Colorization usingoptimization [C] //Computer Graphics Proceedings,Annual Conference Series, ACM SIGGRAPH. New York:ACM, 2004: 689-694.
  • 4WELSH T, ASHIKHMIN M, MUELLER K. Transferringcolor to greyscale images [C] //Computer GraphicsProceedings, Annual Conference Series, ACMSIGGRAPH. New York: ACM, 2002: 277-280.
  • 5MAIRAL J, ELAD M, SAPIRO G. Sparse representationfor color image restoration [J]. IEEE Transcations onImage Processing, 2008, 17(1): 53-69.
  • 6DONOHO D L. Compressed sensing [J]. IEEETranscations on Information Theory, 2006, 52(4): 1289-1306.
  • 7PANG J H, AU O C, TANG K T, et al. Imagecolorization using sparse representation acoustics [C] //Speech and Signal Processing, IEEE InternationalConference on. Piscataway, NJ: IEEE, 2013: 1578-1582.
  • 8TROOP J A, GILBERT A C. Signal recovery fromrandom measurements via orthogonal matching pursuit[J]. IEEE Transactions on Information Theory, 2007,53(12): 4655-4666.
  • 9AHARON M, ELAD M, BRUCKSTEIN A. K-SVD: analgorithm for designing overcomplete dictionaries forsparse representation[J]. IEEE Transsactions on SignalProcessing, 2006, 54(11): 4311-4322.
  • 10GAO S, TSANG I, MA Y. Learning category-specificdictionary and shared dictionary for fine-grained imagegategorization [J]. IEEE Transactions on ImageProcessing, 2014, 23(2): 623-634.

引证文献8

二级引证文献25

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部