Image representations for object detection using kernel classifiers

@inproceedings{Evgeniou2000ImageRF,
  title={Image representations for object detection using kernel classifiers},
  author={Theodoros Evgeniou and Massimiliano Pontil and Constantine Papageorgiou and Tomaso A. Poggio},
  year={2000}
}
This paper presents experimental comparisons of various image representations for object detection using kernel classifiers. In particular it discusses the use of support vector machines (SVM) for object detection using as image representations raw pixel values, projections onto principal components, and Haar wavelets. General linear transformations of the images through the choice of the kernel of the SVM are considered. Experiments showing the effects of histogram equalization, a non-linear… CONTINUE READING
27 Citations
23 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 27 extracted citations

Similar Papers

Loading similar papers…