Distortion Invariant Object Recognition in the Dynamic Link Architecture

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. Schneider.  Berichte der Bunsengesellschaft für Physikalische Chemie , 1967 .

[2]  D. Casasent,et al.  Position, rotation, and scale invariant optical correlation. , 1976, Applied optics.

[3]  C. Malsburg,et al.  How patterned neural connections can be set up by self-organization , 1976, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[4]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[5]  C. A. R. Hoare,et al.  Communicating sequential processes , 1978, CACM.

[6]  David S. Johnson,et al.  Computers and In stractability: A Guide to the Theory of NP-Completeness. W. H Freeman, San Fran , 1979 .

[7]  D J Willshaw,et al.  A marker induction mechanism for the establishment of ordered neural mappings: its application to the retinotectal problem. , 1979, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[8]  Gary L. Miller,et al.  Isomorphism testing for graphs of bounded genus , 1980, STOC '80.

[9]  D. Burr.  A dynamic model for image registration , 1981 .

[10]  David J. Burr,et al.  Elastic Matching of Line Drawings , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  H. A.F.,et al.  DEVELOPMENT OF RETINOTOPIC PROJECTIONS: AN ANALYTIC TREATMENT , 1983 .

[12]  Ch. von der Malsburg,et al.  How are Nervous Structures Organized , 1983 .

[13]  C. Malsburg.  Nervous Structures with Dynamical Links , 1985 .

[14]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[15]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[16]  Richard Durbin,et al.  An analogue approach to the travelling salesman problem using an elastic net method , 1987, Nature.

[17]  D J Field,et al.  Relations between the statistics of natural images and the response properties of cortical cells. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[18]  R Kree,et al.  Recognition of topological features of graphs and images in neural networks , 1988 .

[19]  Christoph von der Malsburg,et al.  Pattern recognition by labeled graph matching , 1988, Neural Networks.

[20]  H. Haken,et al.  Pattern recognition and associative memory as dynamical processes in a synergetic system. I. Translational invariance, selective attention, and decomposition of scenes. , 1988, Biological cybernetics.

[21]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[22]  D. Burr,et al.  Evidence for edge and bar detectors in human vision , 1989, Vision Research.

[23]  C. von der Malsburg,et al.  Distortion invariant object recognition by matching hierarchically labeled graphs , 1989, International 1989 Joint Conference on Neural Networks.

[24]  W. Singer,et al.  Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties , 1989, Nature.

[25]  Joachim M. Buhmann,et al.  Size and distortion invariant object recognition by hierarchical graph matching , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[26]  Joachim M. Buhmann,et al.  Pattern Segmentation in Associative Memory , 1990, Neural Computation.

[27]  Lawrence Sirovich,et al.  Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Petar D. Simic,et al.  Statistical mechanics as the underlying theory of ‘elastic’ and ‘neural’ optimisations , 1990 .

[29]  G Tononi,et al.  Modeling perceptual grouping and figure-ground segregation by means of active reentrant connections. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[30]  Petar D. Simic.  Constrained Nets for Graph Matching and Other Quadratic Assignment Problems , 1991, Neural Comput..

[31]  H. Haken.  Simultaneous Invariance with Respect to Translation, Rotation and Scaling , 1991 .

[32]  Christoph von der Malsburg,et al.  The Correlation Theory of Brain Function , 1994 .