Recognition with local features: the kernel recipe
- 1 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 15, 257-264 vol.1
- https://doi.org/10.1109/iccv.2003.1238351
Abstract
Recent developments in computer vision have shown that local features can provide efficient representations suitable for robust object recognition. Support vector machines have been established as powerful learning algorithms with good generalization capabilities. We combine these two approaches and propose a general kernel method for recognition with local features. We show that the proposed kernel satisfies the Mercer condition and that it is, suitable for many established local feature frameworks. Large-scale recognition results are presented on three different databases, which demonstrate that SVMs with the proposed kernel perform better than standard matching techniques on local features. In addition, experiments on noisy and occluded images show that local feature representations significantly outperform global approaches.Keywords
This publication has 16 references indexed in Scilit:
- A pure learning approach to background-invariant object recognition using pedagogical support vector learningPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Illumination insensitive eigenspacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Viewpoint invariant texture matching and wide baseline stereoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Kernel machine based learning for multi-view face detection and pose estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Matching shapesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Support vector machines for histogram-based image classificationIEEE Transactions on Neural Networks, 1999
- A morphable model for the synthesis of 3D facesPublished by Association for Computing Machinery (ACM) ,1999
- Support vector machines for 3D object recognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- Local grayvalue invariants for image retrievalIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997
- Color indexingInternational Journal of Computer Vision, 1991