This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Distortion Invariant Object Recognition in the Dynamic Link Architecture
March 1993 (vol. 42 no. 3)
pp. 300-311

An object recognition system based on the dynamic link architecture, an extension to classical artificial neural networks (ANNs), is presented. The dynamic link architecture exploits correlations in the fine-scale temporal structure of cellular signals to group neurons dynamically into higher-order entities. These entities represent a rich structure and can code for high-level objects. To demonstrate the capabilities of the dynamic link architecture, a program was implemented that can recognize human faces and other objects from video images. Memorized objects are represented by sparse graphs, whose vertices are labeled by a multiresolution description in terms of a local power spectrum, and whose edges are labeled by geometrical distance vectors. Object recognition can be formulated as elastic graph matching, which is performed here by stochastic optimization of a matching cost function. The implementation on a transputer network achieved recognition of human faces and office objects from gray-level camera images. The performance of the program is evaluated by a statistical analysis of recognition results from a portrait gallery comprising images of 87 persons.

[1] C. von der Malsburg, "The correlation theory of brain function," Internal Report, Max-Planck-Institut für Biophysikalische Chemie, Postfach 2841, D-3400 Göttingen, FRG, 1981.
[2] C. von der Malsburg, "How are nervous structures organized?," inSynergetics of the Brain, Proc. Int. Symp. Synergetics, E. Basar, H. Flohr, H. Haken, and A. Mandell, Eds. Berlin, Germany: Springer, May 1983, pp. 238-249.
[3] C. von der Malsburg, "Nervous structures with dynamical links,"Berichte der Bunsengesellschaft für Physikalische Chemie, vol. 89, pp. 703-710, 1985.
[4] J. Buhmann, J. Lange, and C. von der Malsburg, "Distortion invariant object recognition by matching hierarchically labeled graphs," inProc. IJCNN Int. Conf. Neural Networks, Washington, DC, IEEE, 1989, pp. I 155-159.
[5] E. Bienenstock and R. Doursat, "Issues of representation in neural networks," inVision and Vision Research, A. Gorea, Ed. Cambridge, MA: Cambridge University Press, 1991.
[6] C. von der Malsburg and W. Schneider, "A neural cocktail-party processor,"Biol. Cybern., vol. 54, pp. 29-40, 1986.
[7] W. Schneider, "Anwendung der Korrelationstheorie der Hirnfunktion auf das akustische Figur-Hintergrund-Problem (Cocktailparty-Effekt)," Ph.D. dissertation, Universität Göttingen, 3400 Göttingen, F.R.G., 1986.
[8] O. Sporns, G. Tononi, and G. Edelman, "Modeling perceptual grouping and figure-ground segregation by means of active reentrant connections,"Proc. Nat. Acad. Sci. U.S.A., vol. 88, pp. 129-133, 1991.
[9] C. von der Malsburg and J. Buhmann, "Sensory segmentation with coupled neural oscillators,"Biol. Cybern., pp. 233-242, 1992.
[10] C. M. Gray, P. König, A. K. Engel, and W. Singer, "Oscillatory responses in cat visual cortex exhibit intercolumnar synchronization which reflects global stimulus properties,"Nature, vol. 338, pp. 334-337, 1989.
[11] D. J. Burr, "Elastic matching of line drawings,"IEEE Trans. Pattern Anal. Machine Intell., vol. 3, pp. 708-713, 1981.
[12] D. J. Burr, "A dynamic model for image registration,"Comput. Graphics and Image Processing, vol. 15, pp. 102-112, 1981.
[13] C. von der Malsburg, "Pattern recognition by labeled graph matching,"Neural Networks, vol. 1, pp. 141-148, 1988.
[14] R. Krey and A. Zippelius, "Recognition of topological features of graphs and images in neural networks,"J. Phys. A, vol. 21, pp. 813-818, 1988.
[15] D. J. Willshaw and C. von der Malsburg, "How patterned neural connections can be set up by self-organization,"Proc. Royal Soc., London, vol. B 194, pp. 431-445, 1976.
[16] D. J. Willshaw and C. von der Malsburg, "A marker induction mechanism for the establishment of ordered neural mappings,"Philosophical Trans. Royal Soc., London, vol. B 287, pp. 203-243, 1979.
[17] A. F. Häussler and C. von der Malsburg, "Development of retinotopic projections--An analytical treatment,"J. Theoret. Neurobiol., vol. 2, pp. 47-73, 1983.
[18] J. Buhmann, M. Lades, and C. von der Malsburg, "Size and distortion invariant object recognition by hierarchical graph matching," inProc. IJCNN Int. Conf. Neural Networks, San Diego, CA, IEEE, 1990, pp. II 411-416.
[19] D. Field, "Relations between the statistics of natural images and the response properties of cortical cells,"J. Opt. Soc. Amer. A, vol. 4, no. 12, pp. 2379-2394, 1987.
[20] J. Jones and L. Palmer, "An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex,"J. Neurophysiol., 1987, pp. 1233-1258.
[21] D. Burr, M. Morrone, and D. Spinelli, "Evidence for edge and bar detectors in human vision,"Vision Res., vol. 29, no. 4, pp. 419-431, 1989.
[22] M. R. Garey and D. S. Johnson,Computers and Intractability: A Guide to Theory of NP-Completeness. San Francisco, CA: Freeman, 1979.
[23] R. Durbin and D. Willshaw, "An analogue approach to the travelling salesman problem using an elastic net method,"Nature, vol. 326, pp. 689-691, 1987.
[24] G. Miller, "Isomorphism testing for graphs of bounded genus," inProc. 12th ACM STOC Symp., 1980, pp. 218-224.
[25] R. P. Würtz, J. C. Vorbrüggen, C. von der Malsburg, and J. Lange, "A Transputer-based neural object recognition system," inFrom Pixels to Features II--Parallelism in Image Processing, H. Burkhardt, Y. Neuvo, and J. Simon, Eds. Amsterdam, The Netherlands: North Holland, 1991, pp. 275-294.
[26] C.A.R. Hoare,Communicating Sequential Processes, Prentice Hall, Englewood, N.J., 1985.
[27] T. Kohonen,Self-Organization and Associative Memory. Berlin, Germany: Springer-Verlag, 1988, p. 132.
[28] L. Sirovich and M. Kirby, "Low-dimensional procedure for the characterization of human faces,"J. Opt. Soc. Amer. A, vol. 4, 1987.
[29] M. Kirby and L. Sirovich, "Application of the Karhunen-Loeve procedure for the characterization of human faces,"IEEE Trans. Pattern Anal. Machine Intell., vol. 12, 1990.
[30] D. Cassasent and D. Psaltis, "Position, rotation and scale invariant optical correlation,"Appl. Opt., vol. 15, 1976.
[31] A. Fuchs and H. Haken, "Pattern recognition and associative memory as dynamical processes in a synergetic system. Translational invariance, selective attention, and decomposition of scenes,"Biol. Cybern., vol. 60, pp. 17-22, 1988.
[32] A. Fuchs and H. Haken, "Pattern recognition and associative memory as dynamical processes in a synergetic system. II. Decomposition of complex scenes, simultaneous invariance with respect to translation, rotation, and scaling,"Biol. Cybern., vol. 60, pp. 107-109, 1988.
[33] P. Simic, "Statistical mechanics as the underlying theory of "elastic" and "neural" optimizations,"Network, vol. 1, pp. 89-103, 1990.
[34] P. Simic, "Constrained nets for graph matching and other quadratic assignment problems,"Neural Computation, vol. 3, pp. 268-281, 1991.
[35] D. Wang, J. Buhmann, and C. von der Malsburg, "Pattern segmentation in associative memory,"Neural Computation, vol. 2, pp. 94-106, 1990.

Index Terms:
dynamic link architecture; object recognition system; artificial neural networks; fine-scale temporal structure; cellular signals; human faces; video images; sparse graphs; multiresolution description; local power spectrum; geometrical distance vectors; stochastic optimization; matching cost function; transputer network; gray-level camera images; face recognition; self-organising feature maps; transputer systems.
Citation:
M. Lades, J.C. Vorbruggen, J. Buhmann, J. Lange, C. von der Malsburg, R.P. Wurtz, W. Konen, "Distortion Invariant Object Recognition in the Dynamic Link Architecture," IEEE Transactions on Computers, vol. 42, no. 3, pp. 300-311, March 1993, doi:10.1109/12.210173
Usage of this product signifies your acceptance of the Terms of Use.