Building Gabor Filters from Retinal Responses

Authors: Johannes Partzsch, Christian Mayr, Rene Schuffny

Abstract:

Starting from a biologically inspired framework, Gabor filters were built up from retinal filters via LMSE algorithms. Asubset of retinal filter kernels was chosen to form a particular Gabor filter by using a weighted sum. One-dimensional optimization approaches were shown to be inappropriate for the problem. All model parameters were fixed with biological or image processing constraints. Detailed analysis of the optimization procedure led to the introduction of a minimization constraint. Finally, quantization of weighting factors was investigated. This resulted in an optimized cascaded structure of a Gabor filter bank implementation with lower computational cost.

Keywords: Gabor filter, image processing, optimization

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1074627

References:

[1] Lee, T.S. (1996): Image Representation Using 2D Gabor Wavelets, IEEETransactions on Pattern Analysis and Machine Intelligence, Vol. 18,Issue 10, pp. 951-979
[2] Xu, Y., Zhang, X. (2005): Gabor Filterbank and its Application in theFingerprint Texture Analysis, PDCAT 2005, pp. 829-831
[3] Huang, L., Shimizu, A., Kobatake, H. (2004): Classification-Based Face Detection Using Gabor Filter Features, Proceedings to the 6. IEEE International Conference on Automatic Face and Gesture Recognition,pp. 397-402
[4] Jain, A.K., Prabhakar, S., Hong, L., Pankanti, S. (2000): Filterbank-Based Fingerprint Matching, IEEE Transactions on Image Processing,Vol. 9, Issue 5, pp. 846-859
[5] Jones, J.P., Palmer, L.A. (1987): An Evaluation of the Two-Dimensional Gabor Filter Model of Simple Receptive Fields in Cat Striate Cortex,Journal of Neurophysiology, Vol. 58, Issue 6, pp. 1233-1258
[6] Van Essen, D.C., Anderson, C.H. (1995): Information Processing Strate-gies and Pathways in the Primate Visual System in: An Introduction to Neural and Electronic Networks, 2nd ed., Academic Press, Zornetzeret. al., eds., pp. 45-76
[7] Meister, M., Berry, M.J. (1999): The Neural Code of the Retina, Neuron,Vol. 22, pp. 435-450
[8] Jones, J.P., Palmer, L.A. (1987): The Two-Dimensional Spatial Structure of Simple Receptive Fields in Cat Striate Cortex, Journal of Neurophysiology, Vol. 58, Issue 6, pp. 1187-1211
[9] Thiem, J., Wolff, C., Hartmann, G. (2000): Biology-Inspired Early Vision System for a Spike Processing Neurocomputer, Lecture NotesIn Computer Science, Vol. 1811, pp. 387-396
[10] Thiem, J., Hartmann, G. (2000): Biology-inspired Design of Digital Gabor Filters upon a Hexagonal Sampling Scheme, Proceedings of the 15th International Conference on Pattern Recognition
[11] Merwine, D.K., Amthor, F.R., Grzywacz, N.M. (1995): Interaction between center and surround in rabbit retinal ganglion cells, Journal of Neurophysiology, Vol. 73, Issue 4, pp. 1547-1567
[12] Dacey, D., Packer, O.S., Diller, L., Brainard, D., Peterson, B., Lee, B.(2000): Center surround receptive field structure of cone bipolar cells in primate retina, Vision Research, Vol. 40, pp. 1801-1811
[13] Balasuriya, L. S., Siebert, J. P. (2003): A low level vision hierarchy based on an irregularly sampled retina, Proceedings of the International Conference on Computational Intelligence, Robotics and Autonomous Systems, Singapore, December 2003
[14] Daugman, J.G. (1993): Quadrature-phase simple-cell pairs are appropriately described in complex analytic form, Journal of the Optical Society of America A, Vol. 10, Issue 2, pp. 375-377
[15] Sun, Z., Bebis, G., Miller, R. (2005): On-road vehicle detection using evolutionary Gabor filter optimization, IEEE Transactions on Intelligent Transportation Systems, Vol. 6, Issue 2, pp. 125-137
[16] Weldon, T.P., Higgins, W.E., Dunn, D.F. (1995): Gabor filter design for multiple texture segmentation, Optical Engineering Vol. 35, Issue 10, pp.2852-2863