Pruning local feature correspondences using shape context

  title={Pruning local feature correspondences using shape context},
  author={Gustavo Carneiro and Allan D. Jepson},
  journal={Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.},
  pages={16-19 Vol.3}
We propose a novel approach to improve the distinctiveness of local image features without significantly affecting their robustness with respect to image deformations. Local image features have proven to be successful in computer vision tasks involving partial occlusion, background noise, and various types of image deformations. However, the relatively high number of outliers that have to be rejected from the correspondences set, formed during the search for similar features, still plagues this… CONTINUE READING


Publications citing this paper.
Showing 1-9 of 9 extracted citations

Similar Papers

Loading similar papers…