Abstract
This paper aims at examining the efficiency of supervised learning methods in the derivation of color correction functions. From the existing supervised learning techniques, some of the most appealing in this field are: neural networks and support vector machines (SVMs) used for regression. In the last decade, SVMs are especially used on a large scale in classification and regression, their use is still limited in the domain of color restoration of digital paintings, affected by various ill-defined types of degradations. However, as research shows, they can be a promising alternative to other restoration methods. That is why we focused on their use for color restoration of degraded paintings, examining their performance as compared to the experts’ restoration.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baogang W, Yonghuai L, Yunhe P (2003) Using hybrid knowledge engineering and image processing in color virtual restoration of ancient murals. IEEE Trans Knowl Data Eng 5:1338–1343
Barnard K, Funt B (2002) Camera characterization for color research. Color Res Appl 3:153–164
Barni M, Bartolini F, Cappellini V (2000) Image processing for virtual restoration of artwork. IEEE Multimedia. doi:10.1109/93.848424
Barni M, Pelagotti A, Piva A (2005) Image processing for the analysis and conservation of paintings: opportunities and challenges. IEEE Signal Proc Mag 22(5):141–144
Bousquet O, Boucheron S, Lugosi G (2004) Introduction to statistical learning theory. In: Advanced lectures on machine learning. Springer, Berlin/Heidelberg, pp 169–207
Cappellini V, Piva A (2006) Opportunities and issues of image processing for cultural heritage applications. In: Proceedings EUSIPCO 2006
Devlin AK (2002) A review of tone reproduction techniques. Technical Report CSTR-02-005, Department of Computer Science, University of Bristol
Devlin AK (2004) Perceptual fidelity for digital image display. Ph.D. thesis, Univeristy of Bristol
Gunn SR (1998) Support vector machines for classification and regression. Technical report, faculty of engineering, science and mathematics, University of Southampton
Knut N (1999) The restoration of paintings. Konemann, Cologne
Ofer D, Shai SS, Yoram S (2005) Smooth ε-insensitive regression by loss symmetrization. J Mach Learn Res 6:711–741
Pappas M, Pitas I (2000) Digital color restoration of old paintings. IEEE Trans Image Process 9(2):291–294. doi:10.1109/83.821745
Platt J (2000) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Advances in large margin classifiers. MIT Press, Cambridge, MA
Scholkopf B, Bartlett P, Smola A et al (1998) Shrinking the tube: a new support vector regression algorithm. Technical report series, NC2-TR-1998-031
Vapnik VN (1998) Statistical learning theory. Wiley, New York
Vivek A, Gribok AV, Abidi MA (2007) Neural networks letter: machine learning approach to color constancy. Neural Netw 20(5):559–563
Xiangyang L, Dongming L, Yunhe P (2000) Color restoration and image retrieval for Dunhuang Fresco preservation. IEEE Multimedia 7(2):38–42. doi:10.1109/93.848425
Acknowledgments
This work was partially supported by the National Complex “ASTRA” Museum, in the framework of a long-term cooperation agreement no. 3599/14.02.2008.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nemes, P., Gordan, M., Vlaicu, A. (2013). Color Restoration in Cultural Heritage Images Using Support Vector Machines. In: Bock, H., Jäger, W., Winckler, M. (eds) Scientific Computing and Cultural Heritage. Contributions in Mathematical and Computational Sciences, vol 3. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-28021-4_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-28021-4_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-28020-7
Online ISBN: 978-3-642-28021-4
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)