Abstract
We describe a fast algorithm for Gabor filtering, specially designed for multi-scale image representations. Our proposal is based on three facts: first, Gabor functions can be decomposed in gaussian convolutions and complex multiplications which allows the replacement of Gabor filters by more efficient gaussian filters; second, isotropic gaussian filtering is implemented by separable 1D horizontal/vertical convolutions and permits a fast implementation of the non-separable zero-mean Gabor kernel; third, short FIR filters and the à trous algorithm are utilized to build a recursive multi-scale decomposition, which saves important computational resources. Our proposal reduces to about one half the number of operations with respect to state-of-the-art approaches.
Research partially funded by European Project IST 2001 37540 (CAVIAR).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bruno, E., Pellerin, D.: Robust motion estimation using gabor spatial filters. In: Proc. of the 10th European Signal Processing Conference (September 2000)
Burt, P., Adelson, E.: The laplacian pyramid as a compact image code. IEEE Trans. on Communications 4(31), 532–540 (1983)
Crowley, J., Riff, O., Piater, J.: Fast computations of characteristic scale using a half-octave pyramid. In: CogVis 2002, International Workshop on Cognitive Computing, Zurich (October 2002)
Daugman, J.G.: Two-dimensional spectral analysis of cortical receptive field profiles. Vision Research 20, 847–856 (1980)
Fischer, S., Cristóbal, G.: Minimum entropy transform using gabor wavelets for image compression. In: Proc. of Int. Conf. on Image Analysis and Processing, Palermo, Italy (September 2001)
Gabor, D.: Theory of communication. J. IEE 93, 429–459 (1946)
Geusebroek, J.-M., Smeulders, A.W.M., van de Weijer, J.: Fast anisotropic gauss filtering. In: ECCV, vol. (1), pp. 99–112 (2002)
Itti, L., Koch, C.: A saliency-based search mechanism for overt and covert shifts of attention. Vision Research 40, 1489–1506 (2000)
Krueger, V., Sommer, G.: Gabor wavelet networks for object representation. In: DAGM Symposium, Kiel, Germany (September 2000)
Kruizinga, P., Petkov, N., Grigorescu, S.E.: Comparison of texture features based on gabor filters. In: Proc. of the 10th Int. Conf. on Image Analysis and Processing, Venice, Italy, September 1999, pp. 142–147 (1999)
Lee, T.: Image representation using 2d gabor wavelets. IEEE Trans. on Pattern Analysis and Machine Intelligence 18(10) (October 1996)
Mallat, S.: A Wavelet Tour of Signal Processing, 2nd edn. Academic Press, London (1999)
Nestares, O., Navarro, R., Portilla, J.: Efficient spatial-domain implementation of a multiscale image representation based on gabor functions. Journal of Electronic Imaging 7(1), 166–173 (1998)
Randen, T., Husøy: Image representation using 2d gabor wavelets. IEEE Trans. on Pattern Analysis and Machine Intelligence 21(4), 291–310 (1999)
Tangsukson, T., Havlicek, J.P.: Am-fm image segmentation. In: Proc. IEEE Int. Conf. on Image Processing, Vancouver, Canada, September 2000, pp. 104–107 (2000)
Signal University of Southern California and Image Processing Institute. The uscsipi image database, http://sipi.usc.edu/services/database
Young, I., van Vliet, L.: Recursive implementation of the gaussian filter. Signal Processing 44, 139–151 (1995)
Young, I., van Vliet, L., van Ginkel, M.: Recursive gabor filtering. IEEE Trans. on Signal Processing 50(11), 2798–2805 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bernardino, A., Santos-Victor, J. (2005). A Real-Time Gabor Primal Sketch for Visual Attention. In: Marques, J.S., Pérez de la Blanca, N., Pina, P. (eds) Pattern Recognition and Image Analysis. IbPRIA 2005. Lecture Notes in Computer Science, vol 3522. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11492429_41
Download citation
DOI: https://doi.org/10.1007/11492429_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26153-7
Online ISBN: 978-3-540-32237-5
eBook Packages: Computer ScienceComputer Science (R0)