An important requirement for the expression of cognitive structures is the ability to form mental objects by rapidly binding together constituent parts. In this sense, one may conceive the brain's data structure to have the form of graphs whose nodes are labeled with elementary features. These provide a versatile data format with the ability to render the structure of any mental object. Because of the multitude of possible object variations the graphs are required to be dynamic. Upon presentation of an image a so-called model graph should rapidly emerge by binding together memorized subgraphs derived from earlier learning examples driven by the image features. In this model, the richness and flexibility of the mind is made possible by a combinatorial game of immense complexity. Consequently, emergence of model graphs is a laborious task which, in computer vision, has most often been disregarded in favor of employing model graphs tailored to specific object categories like faces in frontal pose. Invariant recognition or categorization of arbitrary objects, however, demands dynamic graphs.
In this work we propose a form of graph dynamics which proceeds in three steps. In the first step position-invariant feature detectors, which decide whether a feature is present in an image, are set up from training images. For processing arbitrary objects these features are small regular graphs, termed parquet graphs, whose nodes are attributed with Gabor amplitudes. Through combination of these classifiers into a linear discriminant that conforms to Linsker's infomax principle a weighted majority voting scheme is implemented. This network, termed the preselection network, is well suited to quickly rule out most irrelevant matches and only leaves the ambiguous cases, so-called model candidates, to be processed in a third step using a rudimentary version of elastic graph matching, a standard correspondence-based technique for face and object recognition. To further differentiate between model candidates with similar features it is asserted that the features be in similar spatial arrangement for the model to be selected. Model graphs are constructed dynamically by assembling model features into larger graphs according to their spatial arrangement. The model candidate whose model graph attains the best similarity to the input image is chosen as the recognized model.
We report the results of experiments on standard databases for object recognition and categorization. The method achieved high recognition rates on identity, object category, and pose, provided that individual object variations are sufficiently covered by learning examples. Unlike many other models the presented technique can also cope with varying background, multiple objects, and partial occlusion.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
M. Arentz. Integration einer merkmalsbasierten und einer korrespondenzbasierten Methode zur Klassifikation von Audiodaten. Master’s thesis, Computer Science, University of Dortmund, D-44221 Dortmund, Germany, 2006
I. Biederman. Recognition-by-components: A theory of human image understanding. Psychological Review, 94:115–147, 1987
E. Bienenstock and S. Geman. Compositionality in neural systems. In M.A. Arbib, editor, The Handbook of Brain Theory and Neural Networks, pages 223–226. MIT, Cambridge, MA, London, England, 1995
H. Bunke. Graph grammars as a generative tool in image understanding. In M. Nagl H. Ehrig and G. Rozenberg, editors, Graph Grammars and their Application to Computer Science, volume 153, LNCS, pages 8–19. Springer, Berlin Heidelberg New York, 1983
M.A. Eshera and K.S. Fu. An image understanding system using attributed symbolic representation and inexact graph-matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(5):604–618, 1986
L. Fei-Fei, R. Fergus, and P. Perona. A Bayesian approach to unsupervised one-shot learning of object categories. In Proceedings of the Ninth IEEE International Conference on Computer Vision, volume 2, pages 1134–1141, 2003
G. Fritz, L. Paletta, and H. Bischof. Object recognition using local information content. In J. Kittler, M. Petrou, and M. Nixon, editors, 17th International Conference on Pattern Recognition (ICPR 2004), volume 2, pages 15–18, Cambridge, UK. IEEE Press, 2004
B. Fritzke. A self-organizing network that can follow non-stationary distributions. In International Conference on Artificial Neural Networks (ICANN 1997), pages 613–618. Springer, Berlin Heidelberg New York, 1997
R. Gray. Vector quantization. IEEE Signal Processing Magazine, 1(2):4–29, April 1984
D.O. Hebb. The Organization of Behavior. Wiley, New York, 1949
M. Lades, J.C. Vorbrüggen, J. Buhmann, J. Lange, C. von der Malsburg, R.P. Würtz, and W. Konen. Distortion invariant object recognition in the dynamic link architecture. IEEE Transactions on Computers, 42(3):300–310, 1993
L. Lam and S.Y. Suen. Application of majority voting to pattern recognition: An analysis of its behavior and performance. IEEE Transactions on Systems, Man, and Cybernetics – Part A: Systems and Humans, 27(5):553–568, 1997
B. Leibe and B. Schiele. Analyzing appearance and contour based methods for object categorization. In Conference on Computer Vision and Pattern Recognition (CVPR’03), volume 2, pages 409–415, Madison, Wisconsin, USA. IEEE Press, 2003
R. Linsker. Self-organization in a perceptual network. IEEE Computer, 105–117, 1988
N.K. Logothetis and J. Pauls. Psychophysical and physiological evidence for viewer-centered object representation in the primate. Cerebral Cortex, 3:270–288, 1995
H.S. Loos. User-Assisted Learning of Visual Object Recognition. PhD thesis, University of Bielefeld, Germany, 2002
W.S. McCulloch and W.H. Pitts. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5:115–133, 1943
B.W. Mel. SEEMORE: Combining color, shape, and texture histogramming in a neurally inspired approach to visual object recognition. Neural Computation, 9:777–804, 1997
B.T. Messmer and H. Bunke. A new algorithm for error-tolerant subgraph isomorphism detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(5):493–504, 1998
H. Murase and S.K. Nayar. Visual learning and recognition of 3-d objects from appearance. International Journal of Computer Vision, 14:5–24, 1995
S.A. Nene, S.K. Nayar, and H. Murase. Columbia object image library (COIL-100). Technical Report CUCS-006-96, Columbia University, 1996
T.J. Palmeri and I. Gauthier. Visual object understanding. Nature Reviews Neuroscience, 5:291–304, 2004
D.I. Perret, P.A.J. Smith, D.D. Potter, A.J. Mistlin, A.S. Head, and A.D. Milner. Visual cells in the temporal cortex sensitive to face view and gaze direction. Proceedings of the Royal Society B, 223:293–317, 1985
M. Pötzsch, T. Maurer, L. Wiskott, and C. von der Malsburg. Reconstruction from graphs labeled with responses of gabor filters. In C. von der Malsburg, W. von Seelen, J. Vorbrüggen, and B. Sendhoff, editors, Proceedings of the ICANN 1996, pages 845–850, Springer, Berlin, Heidelberg, New York, 1996
M. Riesenhuber and T. Poggio. Models of object recognition. Nature Neuroscience, 3:1199–1204, 2000
F. Rosenblatt. The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65:386–408, 1958
P.A. Schmidt and G. Westphal. Object manipulation by integration of visual and tactile representations. In Uwe J. Ilg, Heinrich H. Bülthoff, and Hanspeter A. Mallot, editors, Dynamic Perception, pages 101–106. infix Verlag/IOS press, 2004
L.B. Shams. Development of visual shape primitives. PhD thesis, University of Southern California, 1999
C.E. Shannon. A mathematical theory of communication. Bell Systems Technical Journal, 27:623–656, 1948
L.G. Shapiro and R.M. Haralick. Structural descriptions and inexact matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 3(5):504–519, 1981
F. Tang and H. Tao. Object tracking with dynamic feature graph. In Proceedings of the 2nd Joint IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, pages 25–32, Beijing, China, 2005
A. Tewes. A flexible object model for encoding and matching human faces. PhD thesis, Physics Department, University of Bochum, Germany, January 2006
S. Thorpe, D. Fize, and C. Marlot. Speed of processing in the human visual system. Nature, 381:520–522, 1996
S. Thorpe and M.F. Thorpe. Seeking categories in the brain. Neuroscience, 291:260–263, 2001
I. Ulusoy and C.M. Bishop. Generative versus discriminative methods for object recognition. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), volume 2, pages 258–265,San Diego, California, USA. IEEE Press, 20–26 June 2005
M. Vidal-Naquet and S. Ullman. Object recognition with informative features and linear classification. In Conference on Computer Vision and Pattern Recognition (CVPR’03), pages 281–288, Madison, Wisconsin, USA. IEEE Press, 2003
C. von der Malsburg. The Correlation theory of brain function. Internal Report 81-2, Max-Planck-Institute for Biophysical Chemistry, Department of Neurobiology, 1981
C. von der Malsburg. Pattern recognition by labeled graph matching. Neural Networks, 1:141–148, 1988
C. von der Malsburg. The dynamic link architecture. In M.A. Arbib, editor, The Handbook of Brain Theory and Neural Networks, 2nd edn., pages 1002–1005. MIT, Cambridge, MA, London, England, 2002
C. von der Malsburg and K. Reiser. Pose invariant object recognition in a neural system. In F. Fogelmann-Soulié, J.C. Rault, P. Gallinari, and G. Dreyfus, editors, International Conference on Artifical Neural Networks (ICANN 1995), pages 127–132. EC2 & Cie, Paris, France, 1995
M. Weber, M. Welling, and P. Perona. Unsupervised learning of models for recognition. In Proceedings of the 6th European Conference on Computer Vision (ECCV), pages 18–32, Dublin, Ireland, 2000
H. Wersing and E. Körner. Learning optimized features for hierarchical models of invariant object recognition. Neural Computation, 15:1559–1588, 2003
G. Westphal. Classification of molecules into classes of toxicity. Technical Report, Dr. Holthausen GmbH, Bocholt, Germany, 2004
G. Westphal. Feature-driven emergence of model graphs for object recognition and categorization. PhD thesis, University of Lübeck, Germany, 2006
G. Westphal and R.P. Würtz. Fast object and pose recognition through minimum entropy coding. In J. Kittler, M. Petrou, and M. Nixon, editors, 17th International Conference on Pattern Recognition (ICPR 2004), volume 3, pages 53–56, Cambridge, UK. IEEE Press, 2004
L. Wiskott. Labeled graphs and dynamic link matching for face recognition and scene analysis. PhD thesis, Physics Department, University of Bochum, Germany, 1995
L. Wiskott, J.-M. Fellous, N. Krüger, and C. von der Malsburg. Face Recognition by elastic bunch graph matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(7):775–779, 1997
I.H. Witten and E. Frank. Data mining: Practical machine learning tools and techniques with java implementations. Morgan Kaufmann, USA, 2000
R.P. Würtz. Object recognition robust under translations, deformations, and changes in background. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(7):769–775, 1997
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Westphal, G., von der Malsburg, C., Würtz, R.P. (2008). Feature-Driven Emergence of Model Graphs for Object Recognition and Categorization. In: Bunke, H., Kandel, A., Last, M. (eds) Applied Pattern Recognition. Studies in Computational Intelligence, vol 91. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76831-9_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-76831-9_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76830-2
Online ISBN: 978-3-540-76831-9
eBook Packages: EngineeringEngineering (R0)