Efficient Sequential Correspondence Selection by Cosegmentation

@article{Cech2008EfficientSC,
  title={Efficient Sequential Correspondence Selection by Cosegmentation},
  author={Jan Cech and Jiri Matas and Michal Perdoch},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2008},
  volume={32},
  pages={1568-1581}
}
In many retrieval, object recognition, and wide-baseline stereo methods, correspondences of interest points (distinguished regions) are commonly established by matching compact descriptors such as SIFTs. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that 1) has high precision (is highly discriminative), 2) has good recall, and 3) is fast. The sequential decision on the correctness of a… CONTINUE READING
Highly Cited
This paper has 67 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 46 extracted citations

68 Citations

01020'10'12'14'16'18
Citations per Year
Semantic Scholar estimates that this publication has 68 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 23 references

Statistical Pattern Recognition Toolbox for Matlab

  • V. Franc, V. Hlavac
  • 2007
1 Excerpt

Simultaneous object recognition and segmentation from single or multiple image

  • V. Ferrari, T. Tuytelaars, L. van Gool
  • views. IJCV,
  • 2006
2 Excerpts

Similar Papers

Loading similar papers…