Sciweavers

Share
CVPR
2008
IEEE

Efficient sequential correspondence selection by cosegmentation

10 years 2 months ago
Efficient sequential correspondence selection by cosegmentation
In many retrieval, object recognition and wide baseline stereo methods, correspondences of interest points are established possibly sublinearly by matching a compact descriptor such as SIFT. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that has (i) high precision (is highly discriminative) (ii) good recall and (iii) is fast. The sequential decision on the correctness of a correspondence is based on trivial attributes of a modified dense stereo matching algorithm. The attributes are projected on a prominent discriminative direction by SVM. Wald's sequential probability ratio test is performed for SVM projection computed on progressively larger co-segmented regions. Experimentally we show that the process significantly outperforms the standard correspondence selection process based on SIFT distance ratios on challenging matching problems.
Jan Cech, Jiri Matas, Michal Perdoch
Added 12 Oct 2009
Updated 28 Oct 2009
Type Conference
Year 2008
Where CVPR
Authors Jan Cech, Jiri Matas, Michal Perdoch
Comments (0)
books