Christoph von der Malsburg
Professor of Computer Science, Computer Science Department, Biology Department, Department for Physics and Astronomy Director, Laboratory of Computational and Biological Vision Director, Institut für Neuroinformatik, Ruhr-Universität Bochum, Germany
- Functional modeling of vision processes
- Computer simulation
- Cognitive architecture
- Figure-ground separation
- Invariant object recognition
Research OverviewBackground to all activities in the LCBV (Laboratory for Computational and Biological Vision) is the attempt to better define the cognitive architecture of the brain, that is, the nervous system's physical data and process structure underlying all cognitive phenomena. This attempt has led to the Dynamic Link Architecture, which is based on temporal binding and rapid reversible synaptic plasticity (see "The Correlation Theory of Brain Function").
The concrete work of the lab is concentrated on the development of functional models of vision processes. One focus is visual segmentation (figure-ground segregation, Gestalt formation) by fusion of multiple cues (motion, texture, recognized form, etc.). The other focus is invariant object recognition. The laboratory has pioneered the usage of fields of Gabor wavelet responses (as an idealized version of oriented receptive fields in visual cortex) and object recognition by elastic graph matching (dynamic link matching). A very successful application has been and is human face recognition, where we have developed a leading technology. The face recognition system compares very well to human performance, as evidenced in experiments by Prof. Irving Biederman.
- Web Site:
- Institut für Neuroinformatik
- Office Location:
- HNB 228C
- Office Phone:
- (213) 740-9224
- Lab Location:
- HNB 329 and HNB 228
- Lab Phone:
- (213) 740-7428 (HNB 228)
- (213) 740-1317
- Physics Diploma, University of Heidelberg, 1968.
- Dr. rer. nat. (Physics), University of Heidelberg, 1970.
Eckes C, Triesch J, von der Malsburg C. (2006) Analysis of cluttered scenes using an elastic matching approach for stereo images. Neural Comput. 18(6):1441-71. -PubMed
Junmei Zhu and von der Malsburg C. (2004) Maplets for correspondence-based object recognition. Neural Networks. 17: 1311-1326. -PubMed
Luecke, J and von der Malsburg, C. (2004) Rapid processing and unsupervised learning in a model of the cortical macrocolumn. Neural Computation. 16: 501--533. -PubMed
Prodoehl, C., Wuertz, R.P. and von der Malsburg, C. (2003) Learning the Gestalt rule of collinearity from object motion. Neural Computation. 15: 1865--1896. -PubMed
von der Malsburg C. (2002) Dynamic Link Architecture. The Handbook of Brain Theory and Neural Networks. The MIT Press, second edition, pp. 365--368.
Shams, L. & von der Malsburg, C. (2002) The role of complex cells in object recognition. Vision Research 42: 2547-2554. -PubMed
Shams, L., & von der Malsburg, C. (2002) Acquisition of visual shape primitives. Vision Research 42:2105-2122. -PubMed
J. Triesch and von der Malsburg C. (2001) Democratic integration: Self-organized integration of adaptive cues. Neural Computation 13: 2049--2074. -PubMed
von der Malsburg, C. (1999) The What and Why of Binding: The Modeler's Perspective. Neuron 24: 95--104
L. Wiskott, J.-M. Fellous, N. Krueger and von der Malsburg C.(1997) Face recognition by elastic bunch graph matching. IEEE PAMI 19: 775--779.