Statistical Learning of Visual Feature Hierarchies
- 5 January 2006
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 44
- https://doi.org/10.1109/cvpr.2005.532
Abstract
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 (EM) 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 allows a probabilistic representation of a flexible visual feature hierarchy. For feature detection, evidence is propagated using Nonparametric Belief Propagation (NBP), a recent generalization of particle filtering. 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.Keywords
This publication has 15 references indexed in Scilit:
- Pictorial Structures for Object RecognitionInternational Journal of Computer Vision, 2005
- Tracking loose-limbed peoplePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Scale & Affine Invariant Interest Point DetectorsInternational Journal of Computer Vision, 2004
- Nonparametric belief propagationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Hierarchical image probability (HIP) modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Distinctive Features Should Be LearnedLecture Notes in Computer Science, 2000
- Hierarchical models of object recognition in cortexNature Neuroscience, 1999
- Object recognition from local scale-invariant featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- A Combined Corner and Edge DetectorPublished by British Machine Vision Association and Society for Pattern Recognition ,1988
- Estimating the Dimension of a ModelThe Annals of Statistics, 1978