Reference : Unsupervised learning of visual feature hierarchies
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/387
Unsupervised learning of visual feature hierarchies
English
Scalzo, Fabien [Université de Liège - ULg > Electrical Engineering and Computer Science > INTELSIG > >]
Piater, Justus mailto [Université de Liège - ULg > Electrical Engineering and Computer Science > INTELSIG >]
2005
Machine Learning and Data Mining in Pattern Recognition
Springer-Verlag Berlin
Lecture Notes in Computer Science 3587
243-252
Yes
No
International
978-3-540-26923-6
Berlin
International Conference on Machine Learning and Data Mining
Leipzig
Germany
[en] computer vision ; machine learning ; visual feature hierarchies
[en] We propose an unsupervised, probabilistic method for learning visual feature hierarchies. Starting from local, low-level features computed at interest point locations, the method combines these primitives into high-level abstractions. Our appearance-based learning method uses local statistical analysis between features and Expectation-Maximization to identify and code spatial correlations. Spatial correlation is asserted when two features tend to occur at the same relative position of each other. This learning scheme results in a graphical model that constitutes a probabilistic representation of a flexible visual feature hierarchy. For feature detection, evidence is propagated using Belief Propagation. Each message is represented by a Gaussian mixture where each component represents a possible location of the feature. In experiments, the proposed approach demonstrates efficient learning and robust detection of object models in the presence of clutter and occlusion and under view point changes.
Researchers ; Professionals
http://hdl.handle.net/2268/387
10.1007/b138149
http://www.springerlink.com/content/4bar85rlnrtv0pf5/

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Restricted access
mldm.pdfPublisher postprint467.34 kBRequest copy

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.