Journal article
CODE: Coherence Based Decision Boundaries for Feature Correspondence
- Abstract:
-
A key challenge in feature correspondence is the difficulty in differentiating true and false matches at a local descriptor level. This forces adoption of strict similarity thresholds that discard many true matches. However, if analyzed at a global level, false matches are usually randomly scattered while true matches tend to be coherent (clustered around a few dominant motions), thus creating a coherence based separability constraint. This paper proposes a non-linear regression technique tha...
Expand abstract
- Publication status:
- Published
- Peer review status:
- Peer reviewed
Actions
Authors
Funding
+ Engineering and Physical Research Council
More from this funder
Funding agency for:
Torr, P
Grant:
ERC-2012-AdG 321162-HELIOS
+ European Research Council
More from this funder
Funding agency for:
Torr, P
Grant:
ERC-2012-AdG 321162-HELIOS
Bibliographic Details
- Publisher:
- Institute of Electrical and Electronics Engineers Publisher's website
- Journal:
- IEEE Transactions on Pattern Analysis and Machine Intelligence Journal website
- Volume:
- 40
- Issue:
- 1
- Pages:
- 34-47
- Publication date:
- 2017-01-15
- Acceptance date:
- 2016-12-20
- DOI:
- EISSN:
-
1939-3539
- ISSN:
-
0162-8828
- Pmid:
-
28092524
- Source identifiers:
-
813641
Item Description
- Language:
- English
- Keywords:
- Pubs id:
-
pubs:813641
- UUID:
-
uuid:0e5a62ab-fb69-472f-a1e1-49d49595db62
- Local pid:
- pubs:813641
- Deposit date:
- 2018-01-09
Terms of use
- Copyright holder:
- © 2017 IEEE
- Copyright date:
- 2017
- Notes:
- This is the author accepted manuscript following peer review version of the article. The final version is available online from IEEE at: 10.1109/tpami.2017.2652468
If you are the owner of this record, you can report an update to it here: Report update to this record