Abstract
In this paper we consider the problem of removing achromatic reflections from a picture of a scene taken through a semi-transparent medium, assuming that the reflection pattern is due to a light source or another object located in front of the object of interest. While other works assume the availability of multiple observations, we consider the more challenging problem of having as data a single color image. We suppose a data model where the virtual reflected image combines additively with the real transmitted image of the object, through unknown coefficients. This highly underdetermined problem is handled by means of a blind estimation technique that exploits the strict dependence of the gradients of the three color channels of the ideal image, and their independence from the gradient of the grayscale reflected image. The model parameters are estimated through independent component analysis, and then the component images are estimated through a regularization technique. The whole algorithm is very fast, and its performance is quantitatively evaluated on numerically generated images, and qualitatively tested on real images.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
T. Cronin, N. Shashar, and L. Wolff, “Portable imaging polarimeters,” in Proc. ICPR (1994), Vol. A, pp. 606–609.
K. Nayar, X. Fang, and T. Boult, “Separation of reection components using color and polarization,” Int. J. Comput. Vis. 21, 163–186 (1997).
H. Fujikake, K. Takizawa, T. Aida, H. Kikuchi, T. Fujii, and M. Kawakita, “Electrically-controllable liquid crystal polarizing filter for eliminating reected light,” Opt. Rev. 5, 93–98 (1998).
Y. Schechner, J. Shamir, and N. Kiryati, “Polarizationbased decorrelation of transparent layers: the inclination angle of an invisible surface,” in Proc. Int. Conf. on Computer Vision (Kerkyra, 1999), pp. 814–819.
“Polarization and statistical analysis of scenes containing a semireector,” J. Opt. Soc. Am. A 17, 276–284 (2000).
M. Born and E. Wolf, Principles of Optics (Pergamon, London, 1965).
H. Farid and E. Adelson, “Separating reections and lighting using independent components analysis,” in Proc. CVPR (Ft. Collins, CO, 1999), Vol. 1, pp. 262–267.
A. Bronstein, M. Bronstein, M. Zibulevsky, and Y. Zeevi, “Sparse ICA for blind separation of transmitted and reected images,” Int. J. Imag. Syst. Technol. 15, 84–91 (2005).
E. Beery and A. Yeredor, “Blind separation of reections with relative spatial shifts,” in Proc. ICASSP (Toulouse, 2006), Vol. 5, pp. 625–628.
K. Gai, Z. Shi, and C. Zhang, “Blindly separating mixtures of multiple layers with spatial shifts,” in Proc. CVPR 2008 (Anchorage, 2008), pp. 1–8.
“Blind separation of superimposed images with unknown motions,” in Proc. CVPR 2009 (Miami, 2009), pp. 1881–1888.
X. Guo, X. Cao, and Y. Ma, “Robust separation of reection from multiple images,” in Proc. Int. Conf. on Computer Vision and Pattern Recognition (CVPR) (Columbus, OH, 2014).
N. Kong, Y.-W. Tai, and J. Shin, “A physically-based approach to reection-separation: from physical modeling to constrained optimization,” IEEE Trans. Pattern Anal. Mach. Intellig. 36, 209–221 (2014).
Y. Shih, D. Krishnan, F. Durand, and W. Freeman, “Reection removal using ghosting cues,” in Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) (Boston, MA, June 2015).
A. Levin, A. Zomet, and Y. Weiss, “Separating reections from a single image using local features,” in Proc. ECCV 2004 (Prague, 2004), pp. 306–313.
A. Levin and Y. Weiss, “User assisted separation of reections from a single image using a sparsity prior,” IEEE Trans. Pattern Anal. Mach. Intellig. 29, 1647–1655 (2007).
K. Kayabol, E. Kuruoglu, and B. Sankur, “Image source separation using color channel dependencies,” in Proc. 8th Int. Conf. on Independent Component Analysis and Signal Separation (Paraty, 2009), pp. 499–506.
B. Sarel and M. Irani, “Separating transparent layers through layer information exchange,” in Proc. ECCV 2004, Ser. LNCS, Ed. by T. Pajdla and J(G.) Matas (Springer, Heidelberg, 2004), Vol. LNCS 3024, pp. 328–341.
Q. Yan, E. E. Kuruoglu, X. Yang, Y. Xu, and K. Kayabol, “Separating reections from a single image using spatial smoothness and structure information,” in Proc. LVA/ICA 2010, Ser. Lecture Notes in Computer Science, (Springer, 2010), Vol. LNCS 6365, pp. 637–644.
L. Bedini, P. Savino, and A. Tonazzini, “Removing achromatic reections from color images with application to artwork imaging,” in Proc. 9th IEEE Int. Symp. on Image and Signal Processing and Analysis (ISPA 2015) (Zagreb, 2015), pp. 126–130.
A. Hyvärinen, “Fast and robust fixed-point algorithms for independent component analysis,” IEEE Trans. Neural Networks 10 (3), 626–634 (1999).
Author information
Authors and Affiliations
Corresponding author
Additional information
The article is published in the original.
Luigi Bedini graduated cum laude in Electronic Engineering from the University of Pisa, Italy, in 1968. Since 1970 he has been a Researcher of the Italian National Research Council, Istituto di Scienza e Tecnologie dell’Informazione, Pisa, Italy. His interests have been in modelling, identification, and parameter estimation of biological systems applied to non-invasive diagnostic techniques. At present, his research interest is in the field of digital signal processing, image reconstruction and neural networks applied to image processing. He is co-author of more than 80 scientific papers. From 1971 to 1989, he was Associate Professor of System Theory at the Computer Science Department, University of Pisa, Italy.
Pasquale Savino is senior researcher at Italian National Research Council, Institute for Information Science and Technology. He graduated in Physics at the University of Pisa, Italy, in 1979. His current research interests are multimedia information indexing and retrieval, multimedia content management, ancient document digital analysis and restoration, and digital libraries. He was the principal investigator in many European Research Projects in the field of multimedia content management and retrieval and in digital libraries.
Anna Tonazzini is senior researcher at the Signals and Images Laboratory of the Institute of Information Science and Technologies, Italian National Research Council (CNR) in Pisa. She coordinated several CNR and Regional Projects for basic and applied research in Image Processing and Analysis, Neural Networks and Learning, Computational Biology and Document Analysis, and is co-author of over 100 published papers. She was also the ISTI responsible for the UE Project ISYREADET, and participated in the MUSCLE European NOE. She was Chair of the EUSIPCO2008 Special Session on Restoration of degraded document images, and Guest Editor of the Special Issue on Image and Video Processing for Cultural Heritage of the Eurasip Journal on Image and Video Processing.
Rights and permissions
About this article
Cite this article
Bedini, L., Savino, P. & Tonazzini, A. Removal of achromatic reflections from a single color image. Pattern Recognit. Image Anal. 27, 675–685 (2017). https://doi.org/10.1134/S1054661817040034
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661817040034