Abstract
Detecting low-level image features such as edges and ridges with spatial filters is improved if the scale of the features are known a priori. Scale-space representations and wavelet pyramids address the problem by using filters over multiple scales. However, the scales of the filters are still fixed beforehand and the number of scales is limited by computational power. The filtering operations are thus not adapted to detect image structures at their optimal or intrinsic scales. We adopt the steering approach to obtain filter responses at arbitrary scales from a small set of filters at scales chosen to accurately sample the “scale space” within a given range. In particular, we use the Moore-Penrose inverse to learn the steering coefficients, which we then regress by polynomial function fitting to the scale parameter in order to steer the filter responses continuously across scales. We show that the extrema of the polynomial steering functions can be easily computed to detect interesting features such as phase-independent energy maxima. Such points of energy maxima in our α-scale-space correspond to the intrinsic scale of the filtered image structures. We apply the technique to several well-known images to segment image structures which are mostly characterised by their intrinsic scale.
Chapter PDF
References
Simoncelli, E., Freeman, W.: The steerable pyramid: A flexible architecture for multi-scale derivative computation. In: IEEE Second International Conference on Image Processing (1995)
Fdez-Valdivia, J., Garcia, J., Martinez-Baena, J., Fdez-Vidal, X.: The selection of natural scales in 2d images using adaptive Gabor filtering. IEEE Transactions on Pattern Analysis and Machine Intelligence 20, 458–469 (1998)
Lindeberg, T.: Principles for automatic scale selection. In: Handbook on Computer Vision and Applications, vol. 2, pp. 239–274. Academic Press, London (1999)
Kadir, T., Brady, M.: Scale, saliency and image description. International Journal of Computer Vision 45, 83–105 (2001)
Bredfelt, C., Ringach, D.: Dynamics of spatial frequency tuning in macaque v1. Journal of Neuroscience 22, 1976–1984 (2002)
Lindeberg, T., Bretzner, L.: Real-time scale selection in hybrid multi-scale representations. In: Griffin, L.D., Lillholm, M. (eds.) Scale-Space 2003. LNCS, vol. 2695, Springer, Heidelberg (2003)
Crowley, J., Riff, O.: Fast computation of scale normalised gaussian receptive fields. In: Griffin, L.D., Lillholm, M. (eds.) Scale-Space 2003. LNCS, vol. 2695, pp. 584–598. Springer, Heidelberg (2003)
Freeman, W.T., Adelson, E.H.: The design and use of steerable filters. IEEE Transactions on Pattern Analysis and Machine Intelligence 13, 891–906 (1991)
Perona, P.: Deformable kernels for early vision. IEEE Transactions on Pattern Analysis and Machine Intelligence 17, 488–499 (1995)
Bharath, A.A.: Scale steerability of a class of digital filters. Electronics Letters 34, 1087–1088 (1998)
Granlund, G., Knutsson, H.: Signal Processing for Computer Vision. Kluwer Academic Publishers, Dordrecht (1994)
Witkin, A., Terzopoulos, D., Kass, M.: Signal matching through scale space. International Journal of Computer Vision 1, 133–144 (1987)
Duits, R., Felsberg, M., Florack, L., Platel, B.: α scale spaces on a bounded domain. In: Griffin, L.D., Lillholm, M. (eds.) Scale-Space 2003. LNCS, vol. 2695, pp. 494–510. Springer, Heidelberg (2003)
Papoulis, A.: Probability, Random Variables and Stochastic Processes. McGraw-Hill, New York (1984)
Bharath, A.: Steerable filters from Erlang functions. In: British Machine Vision Conference, vol. 1, pp. 144–153 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ng, J., Bharath, A.A. (2004). Steering in Scale Space to Optimally Detect Image Structures. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3021. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24670-1_37
Download citation
DOI: https://doi.org/10.1007/978-3-540-24670-1_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21984-2
Online ISBN: 978-3-540-24670-1
eBook Packages: Springer Book Archive