Abstract
Colour constancy is defined as the ability to estimate the actual colours of objects in an acquired image disregarding the colour of scene illuminant. Despite large variety of existing methods, no colour constancy algorithm can be considered as universal. Among the methods, the gray framework is one of the best-known and most used approaches. This framework has some parameters that should be set with appropriate values to achieve the best performance for each image. In this article, we propose a neural network-based algorithm that aims to automatically determine the best value of gray framework parameters for each image. It is a multi-level approach that estimates the optimal values for the gray framework parameters based on relevant features extracted from the input image. Experimental results on two popular colour constancy datasets show an acceptable improvement over state-of-the-art methods.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Agarwal V, Abidi B, Koschan A and Abidi M 2006 An overview of colour constancy algorithms. J. Pattern Recognition Research 1(1): 42–54
Agarwal V, Gribok A V and Abidi M A 2007 Machine learning approach to colour constancy. Neural Networks 20: 559–563 392
Akhavan T and Ebrahimi Moghaddam M 2010 A New Combining Learning Method for Color Constancy, in 2nd International Conference on Image Processing Theory, Tools and Applications (IPTA)
Akilandeswari U, Nithya R and Santhi B 2012 Review on Feature Extraction Methods in Pattern Classification. European J. Sci. Research 71(2): 265–272
Basu M 2002 Gaussian-Based Edge-Detection Methods—A Survey, IEEE Transactions on Systems, Man, and Cybernetics—Part C: Applications and Reviews 32(3): 252–260
Bianco S, Ciocca G, Cusano C and Schettini R 2010 Automatic colour constancy algorithm selection and combination. Pattern Recognition 43(3): 695–705
Buchsbaum G 1980 A spatial processor model for object colour perception. J. Franklin Institute 310(1): 1–26
Ebner M 2006 Evolving colour constancy. Pattern Recognition Lett. 27: 1220–1229
Ebner M 2007 Colour constancy. Wiley-IS&T Series in Imaging Science and Technology. John Wiley & Sons
Faghih M M and Ebrahimi Moghaddam M 2011 Neural Gray Edge: Improving Gray Edge Algorithm Using Neural Network, in International Conference on Image Processing
Finlayson G D and Hordley S D 2006 Gamut Constrained Illuminant Estimation. Int. J. Comput. Vision 67: 93–109
Freeman W T and Adelson E H 1991 The Design and Use of Steerable Filters. Pattern Analysis and Machine Intelligence, IEEE Transactions on 13(9): 891–906
Funt F and Ciurea B 2003 A Large Image Database for Colour Constancy Research, in IS&T/SID’s Colour Imaging Conference. IS&T - The Society for Imaging Science and Technology, Scottsdale
Gijsenij A and Gevers T 2011 Colour Constancy using Natural Image Statistics and Scene Semantics, IEEE Transactions On Pattern Analysis and Machine Intelligence 33(4): 687–698
Gijsenij A, Gevers T and Lucassen M P 2009 Perceptual analysis of distance measures for colour constancy algorithms. Optical Society of America 26(10): 2243–2256
Gijsenij A, Gevers T and van de Weijer J 2010 Generalized Gamut Mapping using Image Derivative Structures for Colour Constancy. Int. J. Comput. Vision 86: 127–139
Gijsenij A, Lu R and Gevers T 2012 Colour Constancy for Multiple Light Sources. IEEE Transactions on Image Processing 21(2): 697–707
Gupta L, Pathangay V and Patra A et al 2007 Indoor versus Outdoor Scene Classification Using Probabilistic Neural Network. EURASIP J. Advances in Signal Processing 2007: 1–10
Haralick R M, Shanmuga K and Dinstein I 1973 Textural features for image classification. IEEE Transactions on Systems, Man & Cybernetics, Vols. SMC-3, 6: 610–621
Land E 1997 The Retinex Theory of Colour Vision. Scientific American 237(6): 108–128
Lilong S and Brian F 2010 Re-processed Version of the Gehler Colour Constancy Dataset of 568 Images. [Online]. Available: http://www.cs.sfu.ca/~colour/data/
Petrov N, Georgieva A and Jordanov I 2012 Self-organizing maps for texture classification. Neural Comput. and Applic.
Results per Dataset 2013 [Online]. Available: http://colorconstancy.com/?page_id=17
Stanikunas R, Vaitkevicius H and Kulikowski J J 2004 Investigation of colour constancy with a neural network 17: 327–337
Tanis E A and Hogg R V 2001 Probability and Statistical Inference: Prentice Hall
Trezzi G D and Finlayson E 2004 Shades of Gray and Colour Constancy, in Colour Imaging Conference IS&T/SID’s, Scottsdale, Arizona
van de Weijer J, Gevers T and Gijsenij A 2007 Edge-Based Colour Constancy. IEEE Transactions on Image Processing 16(9): 2207–2214
Acknowledgement
We would like to thank Iran National Science Foundation for the financial support for this research work.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
FAGHIH, M.M., KHOSRAVINIA, Z. & MOGHADDAM, M.E. A new colour constancy algorithm based on automatic determination of gray framework parameters using neural network. Sadhana 39, 267–281 (2014). https://doi.org/10.1007/s12046-014-0234-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12046-014-0234-9