CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Tractable and Reliable Registration of 2D Point Sets

Erik Ask ; Olof Enqvist (Institutionen för signaler och system, Bildanalys och datorseende) ; Linus Svärm ; Fredrik Kahl (Institutionen för signaler och system, Bildanalys och datorseende) ; Giuseppe Lippolis
Lecture Notes in Computer Science: 13th European Conference on Computer Vision, ECCV 2014, Zurich, Switzerland, 6-12 September 2014 (0302-9743). Vol. 8689 (2014), p. 393-406.
[Konferensbidrag, refereegranskat]

This paper introduces two new methods of registering 2D point sets over rigid transformations when the registration error is based on a robust loss function. In contrast to previous work, our methods are guaranteed to compute the optimal transformation, and at the same time, the worst-case running times are bounded by a low-degree polynomial in the number of correspondences. In practical terms, this means that there is no need to resort to ad-hoc procedures such as random sampling or local descent methods that cannot guarantee the quality of their solutions. We have tested the methods in several different settings, in particular, a thorough evaluation on two benchmarks of microscopic images used for histologic analysis of prostate cancer has been performed. Compared to the state-of-theart, our results show that the methods are both tractable and reliable despite the presence of a significant amount of outliers.



Denna post skapades 2015-01-08. Senast ändrad 2016-05-24.
CPL Pubid: 210205

 

Läs direkt!


Länk till annan sajt (kan kräva inloggning)