Feature hierarchies for object classification
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15505499) , 220-227 Vol. 1
- https://doi.org/10.1109/iccv.2005.98
Abstract
The paper describes a method for automatically extracting informative feature hierarchies for object classification, and shows the advantage of the features constructed hierarchically over previous methods. The extraction process proceeds in a top-down manner: informative top-level fragments are extracted first, and by a repeated application of the same feature extraction process the classification fragments are broken down successively into their own optimal components. The hierarchical decomposition terminates with atomic features that cannot be usefully decomposed into simpler features. The entire hierarchy, the different features and sub-features, and their optimal parameters, are learned during a training phase using training examples. Experimental comparisons show that these feature hierarchies are significantly more informative and better for classification compared with similar nonhierarchical features as well as previous methods for using feature hierarchies.Keywords
This publication has 13 references indexed in Scilit:
- Scalable discriminant feature selection for image retrieval and recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Scale & Affine Invariant Interest Point DetectorsInternational Journal of Computer Vision, 2004
- Learning to detect objects in images via a sparse, part-based representationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Object class recognition by unsupervised scale-invariant learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Visual features of intermediate complexity and their use in classificationNature Neuroscience, 2002
- Elements of Information TheoryPublished by Wiley ,2001
- Combining Class-Specific Fragments for Object ClassificationPublished by British Machine Vision Association and Society for Pattern Recognition ,1999
- A model of saliency-based visual attention for rapid scene analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989