[1]DU Weiwei.Colorization by classifying the prior knowledge[J].智能系统学报,2011,6(6):556-560.
DU Weiwei.Colorization by classifying the prior knowledge[J].CAAI Transactions on Intelligent Systems,2011,6(6):556-560.
点击复制
DU Weiwei.Colorization by classifying the prior knowledge[J].CAAI Transactions on Intelligent Systems,2011,6(6):556-560.
Colorization by classifying the prior knowledge
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
6
期数:
2011年第6期
页码:
556-560
栏目:
学术论文—人工智能基础
出版日期:
2011-12-25
- Title:
- Colorization by classifying the prior knowledge
- 文章编号:
- 1673-4785(2011)06-0556-05
- 关键词:
- colorization; prior knowledge
- Keywords:
- colorization; prior knowledge
- 分类号:
- TP18
- 文献标志码:
- A
- 摘要:
- When a onedimensional luminance scalar is replaced by a vector of a colorful multidimension for every pixel of a monochrome image, the process is called colorization. However, colorization is underconstrained. Therefore, the prior knowledge is considered and given to the monochrome image. Colorization using optimization algorithm is an effective algorithm for the above problem. However, it cannot effectively do with some images well without repeating experiments for confirming the place of scribbles. In this paper, a colorization algorithm is proposed, which can automatically generate the prior knowledge. The idea is that firstly, the prior knowledge crystallizes into some points of the prior knowledge which is automatically extracted by downsampling and upsampling method. And then some points of the prior knowledge are classified and given with corresponding colors. Lastly, the color image can be obtained by the color points of the prior knowledge. It is demonstrated that the proposal can not only effectively generate the prior knowledge but also colorize the monochrome image according to requirements of user with some experiments.
- Abstract:
- When a onedimensional luminance scalar is replaced by a vector of a colorful multidimension for every pixel of a monochrome image, the process is called colorization. However, colorization is underconstrained. Therefore, the prior knowledge is considered and given to the monochrome image. Colorization using optimization algorithm is an effective algorithm for the above problem. However, it cannot effectively do with some images well without repeating experiments for confirming the place of scribbles. In this paper, a colorization algorithm is proposed, which can automatically generate the prior knowledge. The idea is that firstly, the prior knowledge crystallizes into some points of the prior knowledge which is automatically extracted by downsampling and upsampling method. And then some points of the prior knowledge are classified and given with corresponding colors. Lastly, the color image can be obtained by the color points of the prior knowledge. It is demonstrated that the proposal can not only effectively generate the prior knowledge but also colorize the monochrome image according to requirements of user with some experiments.
- 参考文献/References:
-
［1］WELSH T, ASHIKHIMIN M, MUELLER K. Transferring color to greyscale images［J］. ACM Transactions on Graphics, 2002, 21(3): 277280.
［2］LEVIN A, LISCHINSKI D, WEISS Y. Colorization using optimization［C］//Proceedings of ACM SIGGRAPH 2004. Los Angeles, USA, 2004: 689694.
［3］IRONY R, COHENOR D, LISCHINSKI D. Colorization by example［C］//Proceedings of Eurographics Symposium on Rendering 2005. AirelaVille, Switzerland, 2005: 201210.
［4］HUANG T W, CHEN H T. Landmarkbased sparse color representation for color transfer［C］//The 12th Computer Vision. Kyoto, Japan, 2009: 199204.
［5］MCQUEEN J. Some methods for classification and analysis of multivariate observations［C］//Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. ［S.l.］， 1967: 281297.
［6］JOE H W. Hierarchical grouping to optimize an objective function［J］. Journal of the American Statistical Association, 1963, 58: 236244.
［7］JACK K. Video demystified［M］.3rd ed. Elsevier Science and Technology, 2001: 3547.
［8］BURT P J, ADELSON E H. The Laplacian pyramid as a compact image code［J］. IEEE Trans Commun, 1983, 31(4): 532540.
备注/Memo
Received Data： 2011-08-15.
Corresponding Author： DU Weiwei. E-mail:duweiwei@dit.ac.jp.
About the authors：
DU Weiwei was born in 1978. She received PhD degree from Kyushu University in 2008, and now she is an asstistant professor at Kyoto Institute of Technology. Her current interests include fuzzy clusters and graphspectral algorithms, and she has authored or co authored several technical articles in journals and conference proceedings.
更新日期/Last Update:
2012-02-29