cvpr cvpr2013 cvpr2013-130 cvpr2013-130-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Rahat Khan, Joost van_de_Weijer, Fahad Shahbaz Khan, Damien Muselet, Christophe Ducottet, Cecile Barat
Abstract: Color description is a challenging task because of large variations in RGB values which occur due to scene accidental events, such as shadows, shading, specularities, illuminant color changes, and changes in viewing geometry. Traditionally, this challenge has been addressed by capturing the variations in physics-basedmodels, and deriving invariants for the undesired variations. The drawback of this approach is that sets of distinguishable colors in the original color space are mapped to the same value in the photometric invariant space. This results in a drop of discriminative power of the color description. In this paper we take an information theoretic approach to color description. We cluster color values together based on their discriminative power in a classification problem. The clustering has the explicit objective to minimize the drop of mutual information of the final representation. We show that such a color description automatically learns a certain degree of photometric invariance. We also show that a universal color representation, which is based on other data sets than the one at hand, can obtain competing performance. Experiments show that the proposed descriptor outperforms existing photometric invariants. Furthermore, we show that combined with shape description these color descriptors obtain excellent results on four challenging datasets, namely, PASCAL VOC 2007, Flowers-102, Stanford dogs-120 and Birds-200.
[1] R. Benavente, M. Vanrell, and R. Baldrich. Parametric fuzzy sets for automatic color naming. Journal of the Optical Society of America, 25(10):2582–2593, 2008. 5
[2] B. Berlin and P. Kay. Basic color terms: their universality and evolution. Berkeley: University of California, 1969. 5
[3] Y. Chai, V. S. Lempitsky, and A. Zisserman. Bicos: A bilevel co-segmentation method for image classification. In CVPR, pages 2579–2586, 2012. 7
[4] Y. Chai, E. Rahtu, V. S. Lempitsky, L. J. V. Gool, and A. Zisserman. Tricos: A tri-level class-discriminative cosegmentation method for image classification. In ECCV, 2012. 7
[5] K. Chatfield, V. Lemtexpitsky, A. Vedaldi, and A. Zisserman. The devil is in the details: an evaluation of recent feature encoding methods. In BMVC, pages 76. 1–76. 12, 2011. 7
[6] I. Dhillon, S. Mallela, and R. Kumar. A divisive informationtheoretic feature clustering algorithm for text classification. JMLR, 3: 1265–1287, 2003. 2, 3
[7] N. Elfiky, F. S. Khan, J. van de Weijer, and J. Gonzalez. Discriminative compact pyramids for object and scene recognition. Pattern Recognition, 45(4): 1627–1636, April 2012. 6
[8] G. Finlayson and S. Hordley. Gamut constrained illumination estimation. International Journal of Computer Vision, 67(1):93–109, 2006. 1
[9] B. Fulkerson, A. Vedaldi, and S. Soatto. Class segmentation and object localization with superpixel neighborhoods. In ICCV, October 2009. 6
[10] B. Funt and G. Finlayson. Color constant color indexing. IEEE PAMI, 17(5):522–529, 1995. 2
[11] J. Geusebroek, R. van den Boomgaard, A. Smeulders, and H. Geerts. Color invariance. IEEEPAMI, 23(12): 1338–1350, 2001. 2
[12] T. Gevers and A. Smeulders. Color based object recognition. Pattern Recognition, 32:453–464, 1999. 1, 2
[13] T. Gevers and H. Stokman. Robust histogram construction from colour invariants for object recognition. IEEE PAMI, 26(1): 113–1 18, 2004. 2
[14] F. Khan, R. Anwer, J. van de Weijer, A. Bagdanov, M. Vanrell, and A. Lopez. Color attributes for object detection. In CVPR, 2012. 2, 6
[15] F. Khan, J. Van de Weijer, A. Bagdanov, and M. Vanrell. Portmanteau vocabularies for multi-cue image representation. In Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS 2011), 2011. 3, 7
[16] F. S. Khan, J. van de Weijer, and M. Vanrell. Modulating shape features by color attention for object recognition. International Journal ofComputer Vision (IJCV), 98(1):49–64, 2012. 1, 2, 6, 7
[17] A. Khosla, N. Jayadevaprakash, B. Yao, and L. Fei-Fei. Novel dataset for fine-grained image categorization. In First Workshop on Fine-Grained Visual Categorization, CVPR, Colorado Springs, CO, June 2011. 7
[18] S. Lazebnik, C. Schmid, and J. Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In CVPR, pages 2169–2178, 2006. 7
[19] M.-E. Nilsback and A. Zisserman. Automated flower classification over a large number of classes. In Proceedings of the Indian Conference on Computer Vision, Graphics and Image
[20]
[21]
[22]
[23]
[24]
[25]
[26]
[27] Processing, Dec 2008. 2, 6, 7 S. Shafer. Using color to seperate reflection components. COLOR research and application, 10(4):210–218, Winter 1985. 1, 2 A. Torralba and A. Efros. Unbiased look at dataset bias. In CVPR, pages 1521–1528. IEEE, 2011. 6 K. E. A. van de Sande, T. Gevers, and C. G. M. Snoek. Evaluating color descriptors for object and scene recognition. IEEE PAMI, 32(9): 1582–1596, 2010. 1, 7 J. van de Weijer, C. Schmid, J. Verbeek, and D. Larlus. Learning color names for real-world applications. IEEE Transactions on Image Processing, 18(7): 15 12–1524, july 2009. 1, 5, 6 E. Vazquez, R. Baldrich, J. van de Weijer, and M. Vanrell. Describing reflectances for color segmentation robust to shadows, highlights, and textures. IEEE PAMI, 33(5):917– 930, 2011. 3 P. Welinder, S. Branson, T. Mita, C. Wah, F. Schroff, S. Belongie, and P. Perona. Caltech-UCSD Birds 200. Technical Report CNS-TR-2010-001, California Institute of Technology, 2010. 6 J. Zhang, M. Marszalek, S. Lazebnik, and C. Schmid. Local features and kernels for classification of texture and object catergories: A comprehensive study. IJCV, 73(2):213–218, 2007. 7 X. Zhou, K. Yu, T. Zhang, and T. Huang. Image classification using super-vector coding of local image descriptors. In ECCV, 2010. 7 222888777311