Abstract
We propose a novel class-driven color transformation aimed at semantic labeling. In contrast with other approaches elsewhere in the literature, our approach is a supervised one employing class information to learn a color transformation. Our method maps image color to a target space with maximum pairwise distances between classes and minimum scattering within each of them. To compute the color transformation, we pose the problem in terms of a composition of two mappings. The first mapping employs a pairwise discriminant cost function minimized through a steepest descent optimization to map the image color data onto a space spanned by the class set. It targets better separability between distinct classes as well as less scattering within each individual class. The second mapping corresponds to subspace projection of this class data to a target space with same dimensionality of image color data. To preserve distances attained by the first of the mappings, this subspace projection is effected making use of metric multi-dimensional scaling. We report our experiments on MSRC-21 and SBD datasets, where our method consistently improves overall and average performances of well-known publicly available TextonBoost and DARWIN multiclass segmentation frameworks at a negligible computational cost. These results confirms our contribution towards reflection of higher distinction in color space by imposing better separability in a novel representation which is learned from class information of the dataset under consideration.
National ICT Australia (NICTA) is funded by the Australian Government as represented by the Department of Broadband, Communications and the Digital Economy and the Australian Research Council through the ICT Center of Excellence program.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Van De Sande, K., Gevers, T., Snoek, C.: Evaluating color descriptors for object and scene recognition. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1582–1596 (2010)
Finlayson, G.D., Drew, M.S.: The maximum ignorance assumption with positivity. In: Society for Imaging Science and Technology Conference on Color and Imaging, pp. 202–205 (1996)
Nayar, S.K., Bolle, R.M.: Reflectance based object recognition. Int. J. Comput. Vis. 17(3), 219–240 (1996)
Dror, R.O., Adelson, E.H., Willsky, A.S.: Recognition of surface reflectance properties from a single image under unknown real-world illumination (2001)
Slater, D., Healey, G.: Object recognition using invariant profiles. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 827–832 (1997)
Jacobs, D.W., Belhumeur, P.N., Basri, R.: Comparing images under variable illumination. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 610–617 (1998)
Lin, S., Lee, S.W.: Using chromaticity distributions and eigenspace analysis for pose-, illumination-, and specularity-invariant recognition of 3D objects. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 426–431 (1997)
Lenz, R., Carmona, P.L., Meer, P.: The hyperbolic geometry of illumination-induced chromaticity changes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1–6 (2007)
Chong, H.Y., Gortler, S.J., Zickler, T.: A perception-based color space for illumination-invariant image processing. ACM Trans. Graph. 27(3), 61 (2008)
Strutz, T.: Adaptive selection of colour transformations for reversible image compression. In: IEEE European Signal Processing Conference (EUSIPCO), pp. 1204–1208 (2012)
Hu, G., Liu, C., Chuang, K., Yu, S., Tsui, T.: General regression neural network utilized for color transformation between images on RGB color space. In: IEEE International Conference on Machine Learning and Cybernetics (ICMLC), vol. 4, pp. 1793–1799 (2011)
Wyszecki, G., Stiles, W.S.: Color Science. Wiley, New York (1982)
Meyer, G.W., Greenberg, D.P.: Perceptual color spaces for computer graphics. In: ACM SIGGRAPH Computer Graphics, vol. 14(3), pp. 254–261 (1980)
Fu, Z., Robles-Kelly, A.: Learning object material categories via pairwise discriminant analysis. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) (2007)
McLachlan, G.: Discriminant Analysis and Statistical Pattern Recognition. Wiley, Hoboken (2004)
Loog, M., Duin, R., Haeb-Umbach, R.: Multiclass linear dimension reduction by weighted pairwise Fisher criteria. IEEE Trans. Pattern Anal. Mach. Intell. 23(7), 762–766 (2001)
Bickel, P.J., Levina, E.: Some theory for Fisher’s linear discriminant function, ‘naive Bayes’, and some alternatives when there are many more variables than observations. J. Bernoulli 10, 989–1010 (2004)
Fan, J., Fan, Y.: High dimensional classification using features annealed independence rules. Ann. Stat. 36(6), 2605 (2008)
Tibshirani, R., Hastie, T., Narasimhan, B., Chu, G.: Diagnosis of multiple cancer types by shrunken centroids of gene expression. Proc. Nat. Acad. Sci. 99(10), 6567–6572 (2002)
Krähenbühl, Ph., Koltun, V.: Efficient inference in fully connected crfs with gaussian edge potentials. arXiv preprint arXiv:1210.5644 (2012)
Gould, S.: DARWIN: a framework for machine learning and computer vision research and development. J. Mach. Learn. Res. 13, 3533–3537 (2012)
Shotton, J., Winn, J., Rother, C., Criminisi, A.: Textonboost for image understanding: Multi-class object recognition and segmentation by jointly modeling texture, layout, and context. Int. J. Comput. Vis. 81(1), 2–23 (2009)
Gould, S., Fulton, R., Koller, D.: Decomposing a scene into geometric and semantically consistent regions. In: IEEE International Conference on Computer Vision (ICCV), pp. 1–8 (2009)
Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, New York (2009)
Li, X., Jiang, T., Zhang, K.: Efficient and robust feature extraction by maximum margin criterion. IEEE Trans. Neural Netw. 17(1), 157–165 (2006)
Hastie, T., Tibshirani, R.: Classification by pairwise coupling. Ann. Stat. 26(2), 451–471 (1998)
Harris, C.: Tracking with rigid models. In: Blake, A., Yuille, A. (eds.) Active Vision, pp. 59–73. MIT Press, Cambridge (1993)
Lin, D., Yan, S., Tang, X.: Pursuing informative projection on Grassmann manifold. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, pp. 1727–1734 (2006)
Baudat, G., Anouar, F.: Generalized discriminant analysis using a kernel approach. Neural Comput. 12(10), 2385–2404 (2000)
Wang, X., Tang, X.: Dual-space linear discriminant analysis for face recognition. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, p. 564 (2004)
Geusebroek, J., Van den Boomgaard, R., Smeulders, A.W.M., Geerts, H.: Color invariance. IEEE Trans. Pattern Anal. Mach. Intell. 23(12), 1338–1350 (2001)
Álvarez, J.M., Gevers, T., López, A.M.: Learning photometric invariance for object detection. Int. J. Comput. Vis. 90(1), 45–61 (2010)
Acknowledgement
Authors would like to highly appreciate reviewers’ efforts and positive feedbacks which improve the quality and readability of this work.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Shahriari, A., Alvarez, J.M., Robles-Kelly, A. (2015). Class-Driven Color Transformation for Semantic Labeling. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9005. Springer, Cham. https://doi.org/10.1007/978-3-319-16811-1_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-16811-1_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16810-4
Online ISBN: 978-3-319-16811-1
eBook Packages: Computer ScienceComputer Science (R0)