ICANN 1996: Artificial Neural Networks — ICANN 96 pp 845-850 | Cite as
Reconstruction from graphs labeled with responses of Gabor filters
Poster Presentations 3 Sensory Processing
First Online:
Abstract
The work presented is part of a larger effort to build a general object recognition system. Objects as well as human faces are represented by graphs labeled with Gabor filter responses. We describe an optimal method to reconstruct images from such graphs. Two examples of how this can be used to analyze the object representation or to compensate for its deficiencies are presented. Since the reconstruction method is formulated generally for an arbitray set of linear filters, it can also be applied to data produced by other systems, artificial or biological.
Keywords
Receptive Field Object Recognition Projection Function Object Representation Gabor Filter
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.
Preview
Unable to display preview. Download preview PDF.
References
- 1.M. Lades, J.C. Vorbrüggen, J. Buhmann, J. Lange, C. v.d. Malsburg, R.P. Würtz, and W. Konen. Distortion invariant object recognition in the dynamic link architecture. IEEE Trans. Comput., 42(3):300–311, 1993.Google Scholar
- 2.J. Buhmann, M. Lades, and C. v.d. Malsburg. Size and distortion invariant object recognition by hierarchical graph matching. In Proc. of the IJCNN International Joint Conference on Neural Networks, pages II 411–416, San Diego, June 1990. IEEE.Google Scholar
- 3.L. Wiskott, J.M. Fellous, N. Krüger, and C. v.d. Malsburg. Face recognition and gender determination. In Proc. of the International Workshop on Automatic Face-and Gesture-Recognition, IWAFGR 95, Zurich, June 1995.Google Scholar
- 4.C. v.d. Malsburg. The correlation theory of brain function. Internal report, 81-2, Max-Planck-Institut für Biophysikalische Chemie, Göttingen, FRG, 1981. Reprinted in E. Domany, J.L. van Hemmen, and K.Schulten, editors, Models of Neural Networks II, pages 95–119. Springer, Berlin, 1994.Google Scholar
- 5.L. Wiskott and C. v.d. Malsburg. A neural system for the recognition of partially occluded objects in cluttered scenes. Int. J. of Pattern Recognition and Artificial Intelligence, 7(4):935–948, 1993.Google Scholar
- 6.R.P. Würtz. Multilayer Dynamic Link Networks for Establishing Image Point Correspondences and Visual Object Recognition, volume 41 of Reihe Physik. Verlag Harri Deutsch, Frankfurt a. Main, 1995. PhD thesis.Google Scholar
- 7.J.P. Jones and L.A. Palmer. An evaluation of the two-dimensional gabor filter model of simple receptive fields in cat striate cortex. Journal of Neurophysiology, 58(6):1233–1258, 1987.Google Scholar
- 8.D.J. Field. Relations between the statistics of natural images and the response properties of cortical cells. Optical Society of America, 4(12):2379–2394, 1987.Google Scholar
- 9.J.D. Daugman. Complete discrete 2-d gabor transforms by neural networks for image analysis and compression. IEEE Transactions on Acoustics, Speech, and Signal Processing, 36:1169–1179, 1988.Google Scholar
- 10.M. Pötzsch, N. Krüger, and C. v.d. Malsburg. Improving object recognition by transforming Gabor filter responses. Network: Computation in Neural Systems, 7(2), 1996.Google Scholar
- 11.M. Pötzsch. Die Behandlung der Wavelet-Transformation von Bildern in der Nähe von Objektkanten. Internal Report (IR-INI) 94-04, Institut für Neuroinformatik, Ruhr-Universität Bochum, 1994.Google Scholar
Copyright information
© Springer-Verlag Berlin Heidelberg 1996