C
Christoph von der Malsburg
Researcher at Frankfurt Institute for Advanced Studies
Publications - 125
Citations - 9701
Christoph von der Malsburg is an academic researcher from Frankfurt Institute for Advanced Studies. The author has contributed to research in topics: Cognitive neuroscience of visual object recognition & Gabor wavelet. The author has an hindex of 35, co-authored 124 publications receiving 9527 citations. Previous affiliations of Christoph von der Malsburg include Ruhr University Bochum & University of Southern California.
Papers
More filters
Book
Face recognition by elastic bunch graph matching
TL;DR: In this article, the authors presented a method for recognizing human faces from single images out of a large database with one image per person, based on a novel approach, the bunch graph, which is constructed from a small set of sample image graphs.
Book ChapterDOI
The Correlation Theory of Brain Function
TL;DR: A summary of brain theory is given so far as it is contained within the framework of Localization Theory, according to which synaptic modulation introduces flexibility into cerebral networks which is necessary to solve the invariance problem.
Book ChapterDOI
Face Recognition by Elastic Bunch Graph Matching
Laurenz Wiskott,Jean Marc Fellous,Norbert Krüger,Christoph von der Malsburg,Christoph von der Malsburg +4 more
TL;DR: A system for recognizing human faces from single images out of a large database with one image per person, using the bunch graph, which is constructed from a small set of sample image graphs.
Journal ArticleDOI
A neural cocktail-party processor
TL;DR: The model is an application and illustration of the Correlation Theory of brain function and represents the peripheral evidence represented by amplitude modulations globally present in all components of a sound spectrum.
Journal ArticleDOI
Binding in Models of Perception and Brain Function
TL;DR: Inclusion of temporal binding in neural models has led to recent breakthroughs in solving important perceptual problems, among them is perceptual segmentation, invariant object recognition and natural language parsing, as well as overcoming the ‘learning-time’ barrier.