Christoph von der Malsburg | Goethe-Universität Frankfurt am Main (original) (raw)
Uploads
Papers by Christoph von der Malsburg
Proposing A Neural Mechanism. Transformation-tolerant recognition seems to still pose a hard chal... more Proposing A Neural Mechanism. Transformation-tolerant recognition seems to still pose a hard challenge for artificial vision systems, as opposed to their biological counterparts. We present a neurally-plausible mechanism to establish local feature correspondences between object images at different scales and orientations while using and explicitly representing the information about the given transformations. The fundamental functionality is based on a network of cortical macrocolumns supporting the Dynamic Link Architecture ...
Lecture Notes in Computer Science, 2002
Lecture Notes in Computer Science, 2000
Lecture Notes in Computer Science, 2002
Lecture Notes in Computer Science, 2002
... Perception, 22(12):1483–1501, 1993. 14. M. Weber, M. Welling, and P. Perona. ... 15. Jan Wieg... more ... Perception, 22(12):1483–1501, 1993. 14. M. Weber, M. Welling, and P. Perona. ... 15. Jan Wieghardt and Hartmut S. Loos. Finding Faces in Cluttered Still Images with Few Examples. ... 16. Laurenz Wiskott, Jean-Marc Fellous, Norbert Krüger, and Christoph von der Mals-burg. ...
Proceedings of the International Conference on Neural Computation Theory and Applications, 2014
Understanding Complex Systems, 2008
Classically, programs are written with specific applications in mind. Organic computing will be b... more Classically, programs are written with specific applications in mind. Organic computing will be based on a general architecture, which apart from libraries of standard algorithms will consist of generic mechanisms of organization. Users can then create specific applications by defining goal hierarchies, by instruction and the pointing out of examples. Systems will respond to these influences by adapting control parameters so as to direct the ontogenetic process of self-organization and by organizing sample material.
We present a system for the interpretation of camera images of scenes composed of several known o... more We present a system for the interpretation of camera images of scenes composed of several known objects with mutual occlusion. The scenes are analyzed by the recognition of the objects present and by the determination of their occlusion relations.
illips, Hyeonjoon Moon, Patrick Rauss, and Syed A. Rizvi, "The FERET September 1996 database... more illips, Hyeonjoon Moon, Patrick Rauss, and Syed A. Rizvi, "The FERET September 1996 database and evaluation procedure", in Josef Bigun, G'erard Chollet, and Gunilla Borgefors, editors, Audio- and Video-based Biometric Person Authentication, vol. 1206 of Lecture Notes in Computer Science, pp. 395--402. Springer, March 1997. [40] P. Jonathon Phillips, Hyeonjoon Moon, Patrick Rauss, and Syed A. Rizvi, "The FERET evaluation methodology for face recognition algorithms", in Proceedings of Computer Vision and Pattern Recognition, June 1997. [41] P. Jonathon Phillips, Patrick J. Rauss, and Sandor Z. Der, "FERET (face recognition technology) recognition algorithm development and test results", Technical Report ARL--TR--995, Army Research Laboratory, October 1996. [42] Stephane Pigeon and Luc Vandendorpe, "The M2VTS multimodal face database (release 1.00)", in Audio- and Video-based Biometric Person Authentication, pp. 403--409,
We present here a system for invariant and robust recognition of objects from camera images. The ... more We present here a system for invariant and robust recognition of objects from camera images. The system aspires both to be a model for biological object vision (at least an ontogenetically early form of it) and to be at the cutting edge of technological achievement. Our model is based on the principles of temporal feature binding and dynamic link matching. Objects are stored in the form of two-dimensional aspects. These are competitively matched against current images. During the matching process, complete matrices of dynamic links between the image and all models are refined by a process of rapid selforganization, the final state connecting only corresponding points in image and object models. As data format for representing images we use local sets ("jets") of Gabor-based wavelets. We have tested the performance of our system by having it recognize human faces against data bases of more than one hundred images. The system is invariant with respect to retinal position, an...
British Machine Vision Conference, 1999
The viewing hemisphere of a 3-dimensional object can be partitioned into areas of similar views, ... more The viewing hemisphere of a 3-dimensional object can be partitioned into areas of similar views, termed view bubbles. We compare two procedures of generating view bubbles: tracking of object features, i.e., Gabor wavelet responses, by utilizing the continuity of successive views and matching of features in different views, which are assumed to be independent. Both pro- cedures proved to be
The goal of this research program was to develop novel algorithms, architectures, and hardware fo... more The goal of this research program was to develop novel algorithms, architectures, and hardware for a truly smart camera, with inherent capability for semi-autonomous object recognition as well as optimal image capture. In this research, we combined striking advances in the understanding of the mechanisms of biological vision systems with similar advances in hybrid electronic/photonic packaging technology, in order to develop adaptive, artificial, biologically-inspired vision systems. A key research program objective, therefore, was to establish and address the fundamental scientific and technological issues that currently inhibit the implementation of such adaptive optoelectronic eyes.
Lecture Notes in Computer Science, 2010
Lecture Notes in Computer Science, 2010
Lecture Notes in Computer Science, 2006
Proposing A Neural Mechanism. Transformation-tolerant recognition seems to still pose a hard chal... more Proposing A Neural Mechanism. Transformation-tolerant recognition seems to still pose a hard challenge for artificial vision systems, as opposed to their biological counterparts. We present a neurally-plausible mechanism to establish local feature correspondences between object images at different scales and orientations while using and explicitly representing the information about the given transformations. The fundamental functionality is based on a network of cortical macrocolumns supporting the Dynamic Link Architecture ...
Lecture Notes in Computer Science, 2002
Lecture Notes in Computer Science, 2000
Lecture Notes in Computer Science, 2002
Lecture Notes in Computer Science, 2002
... Perception, 22(12):1483–1501, 1993. 14. M. Weber, M. Welling, and P. Perona. ... 15. Jan Wieg... more ... Perception, 22(12):1483–1501, 1993. 14. M. Weber, M. Welling, and P. Perona. ... 15. Jan Wieghardt and Hartmut S. Loos. Finding Faces in Cluttered Still Images with Few Examples. ... 16. Laurenz Wiskott, Jean-Marc Fellous, Norbert Krüger, and Christoph von der Mals-burg. ...
Proceedings of the International Conference on Neural Computation Theory and Applications, 2014
Understanding Complex Systems, 2008
Classically, programs are written with specific applications in mind. Organic computing will be b... more Classically, programs are written with specific applications in mind. Organic computing will be based on a general architecture, which apart from libraries of standard algorithms will consist of generic mechanisms of organization. Users can then create specific applications by defining goal hierarchies, by instruction and the pointing out of examples. Systems will respond to these influences by adapting control parameters so as to direct the ontogenetic process of self-organization and by organizing sample material.
We present a system for the interpretation of camera images of scenes composed of several known o... more We present a system for the interpretation of camera images of scenes composed of several known objects with mutual occlusion. The scenes are analyzed by the recognition of the objects present and by the determination of their occlusion relations.
illips, Hyeonjoon Moon, Patrick Rauss, and Syed A. Rizvi, "The FERET September 1996 database... more illips, Hyeonjoon Moon, Patrick Rauss, and Syed A. Rizvi, "The FERET September 1996 database and evaluation procedure", in Josef Bigun, G'erard Chollet, and Gunilla Borgefors, editors, Audio- and Video-based Biometric Person Authentication, vol. 1206 of Lecture Notes in Computer Science, pp. 395--402. Springer, March 1997. [40] P. Jonathon Phillips, Hyeonjoon Moon, Patrick Rauss, and Syed A. Rizvi, "The FERET evaluation methodology for face recognition algorithms", in Proceedings of Computer Vision and Pattern Recognition, June 1997. [41] P. Jonathon Phillips, Patrick J. Rauss, and Sandor Z. Der, "FERET (face recognition technology) recognition algorithm development and test results", Technical Report ARL--TR--995, Army Research Laboratory, October 1996. [42] Stephane Pigeon and Luc Vandendorpe, "The M2VTS multimodal face database (release 1.00)", in Audio- and Video-based Biometric Person Authentication, pp. 403--409,
We present here a system for invariant and robust recognition of objects from camera images. The ... more We present here a system for invariant and robust recognition of objects from camera images. The system aspires both to be a model for biological object vision (at least an ontogenetically early form of it) and to be at the cutting edge of technological achievement. Our model is based on the principles of temporal feature binding and dynamic link matching. Objects are stored in the form of two-dimensional aspects. These are competitively matched against current images. During the matching process, complete matrices of dynamic links between the image and all models are refined by a process of rapid selforganization, the final state connecting only corresponding points in image and object models. As data format for representing images we use local sets ("jets") of Gabor-based wavelets. We have tested the performance of our system by having it recognize human faces against data bases of more than one hundred images. The system is invariant with respect to retinal position, an...
British Machine Vision Conference, 1999
The viewing hemisphere of a 3-dimensional object can be partitioned into areas of similar views, ... more The viewing hemisphere of a 3-dimensional object can be partitioned into areas of similar views, termed view bubbles. We compare two procedures of generating view bubbles: tracking of object features, i.e., Gabor wavelet responses, by utilizing the continuity of successive views and matching of features in different views, which are assumed to be independent. Both pro- cedures proved to be
The goal of this research program was to develop novel algorithms, architectures, and hardware fo... more The goal of this research program was to develop novel algorithms, architectures, and hardware for a truly smart camera, with inherent capability for semi-autonomous object recognition as well as optimal image capture. In this research, we combined striking advances in the understanding of the mechanisms of biological vision systems with similar advances in hybrid electronic/photonic packaging technology, in order to develop adaptive, artificial, biologically-inspired vision systems. A key research program objective, therefore, was to establish and address the fundamental scientific and technological issues that currently inhibit the implementation of such adaptive optoelectronic eyes.
Lecture Notes in Computer Science, 2010
Lecture Notes in Computer Science, 2010
Lecture Notes in Computer Science, 2006