Tractable and Reliable Registration of 2D Point Sets
Författare
Redaktör
- David Fleet
- Tomas Pajdla
- Bernt Schiele
- Tinne Tuytelaars
Summary, in English
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-the-art, our results show that the methods are both tractable and reliable despite the presence of a significant amount of outliers.
Avdelning/ar
Publiceringsår
2014
Språk
Engelska
Sidor
393-406
Publikation/Tidskrift/Serie
Lecture Notes in Computer Science (Computer Vision - ECCV 2014, 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I)
Volym
8689
Fulltext
Dokumenttyp
Konferensbidrag
Förlag
Springer
Ämne
- Mathematics
- Computer Vision and Robotics (Autonomous Systems)
Nyckelord
- Optimization
- 2D Registration
- L1 norm
Conference name
13th European Conference on Computer Vision - ECCV 2014
Conference date
2014-09-06 - 2014-09-12
Status
Published
Forskningsgrupp
- Urological cancer, Malmö
- Mathematical Imaging Group
ISBN/ISSN/Övrigt
- ISSN: 0302-9743
- ISSN: 1611-3349
- ISBN: 978-3-319-10589-5 (Print)
- ISBN: 978-3-319-10590-1 (Online)