View-based 3D object recognition with support vector machines
- 20 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Support vector machines have demonstrated excellent results in pattern recognition tasks and 3D object recognition. We confirm some of the results in 3D object recognition and compare it to other object recognition systems. We use different pixel-level representations to perform the experiments, while we extend the setting to the more challenging and practical case when only a limited number of views of the object are presented during training. We report high correct classification of unseen views, especially considering that no domain knowledge is including into the proposed system. Finally, we suggest an active learning algorithm to reduce further the required number of training views.Keywords
This publication has 7 references indexed in Scilit:
- Real-time 100 object recognition systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Support vector machines for 3D object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- Properties of Support Vector MachinesNeural Computation, 1998
- Support-vector networksMachine Learning, 1995
- Visual learning and recognition of 3-d objects from appearanceInternational Journal of Computer Vision, 1995
- A training algorithm for optimal margin classifiersPublished by Association for Computing Machinery (ACM) ,1992
- Psychophysical support for a two-dimensional view interpolation theory of object recognition.Proceedings of the National Academy of Sciences, 1992