Abstract
Calculating a reliable similarity measure between pixel features is essential for many computer vision and image processing applications. We propose a similarity measure (affinity) between pixel features, which depends on the feature space histogram of the image. We use the observation that clusters in the feature space histogram are typically smooth and roughly convex. Given two feature points we adjust their similarity according to the bottleneck in the histogram values on the straight line between them. We call our new similarities Bottleneck Affinities. These measures are computed efficiently, we demonstrate superior segmentation results compared to the use of the Euclidean metric.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Cheng, H.D., Jiang, X., Sun, Y., Wang, J.: Color image segmentation: advances and prospects. Pattern Recognition 34, 2259–2281 (2001)
Tuceryan, M., Jain, A.K.: Texture analysis, pp. 235–276 (1993)
Fowlkes, C., Martin, D., Malik, J.: Learning affinity functions for image segmentation: Combining patch-based and gradient-based approaches. In: Computer Vision and Pattern Recognition, CVPR (2003)
Comaniciu, D., Meer, P.: Robust analysis of feature spaces: color image segmentation. In: CVPR 1997: Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR 1997), vol. 750, p. 750. IEEE Computer Society, Washington, DC, USA (1997)
Mumford, D., Shah, J.: Boundary detection by minimizing functionals, I. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 22–26 (1985)
Vese, L.A., Chan, T.F.: A multiphase level set framework for image segmentation using the mumford and shah model. International Journal of Computer Vision 50, 271–293 (2002)
Spokoiny, V.: Estimation of a function with discontinuities via local polynomial fit with an adaptive window choice. Annals of Statistics, 1356–1378 (1998)
Gevers, T., Smeulders, A.W.M.: Color-based object recognition. Pattern Recognition 32, 453–464 (1999)
Park, S., Schowengerdt, R.: Image sampling, reconstruction, and the effect of sample scene phasing. Applied Optics 21, 3142–3151 (1982)
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI (2000)
Comaniciu, D., Meer, P.: Mean shift analysis and applications. In: ICCV 1999: Proceedings of the International Conference on Computer Vision, vol. 2, p. 1197. IEEE Computer Society, Washington, DC, USA (1999)
Leung, T., Malik, J.: Representing and recognizing the visual appearance of materials using three-dimensional textons. Int. J. Comput. Vision 43, 29–44 (2001)
Schmid, C.: Constructing models for content-based image retrieval. In: International Conference on Computer Vision & Pattern Recognition (2001)
Visual Geometry Group, University of Oxford, http://www.robots.ox.ac.uk/~vgg/research/texclass/filters.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Omer, I., Werman, M. (2006). Image Specific Feature Similarities. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3952. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744047_25
Download citation
DOI: https://doi.org/10.1007/11744047_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33834-5
Online ISBN: 978-3-540-33835-2
eBook Packages: Computer ScienceComputer Science (R0)