Home News About Us Contact Contributors Disclaimer Privacy Policy Help FAQ

Home
Search
Quick Search
Advanced
Fulltext
Browse
Collections
Persons
My eDoc
Session History
Login
Name:
Password:
Documentation
Help
Support Wiki
Direct access to
document ID:


          Institute: MPI für Informatik     Collection: Computer Graphics Group     Display Documents



ID: 520484.0, MPI für Informatik / Computer Graphics Group
Scale Invariant Feature Transform with Irregular Orientation Histogram Binning
Authors:Cui, Yan; Hasler, Nils; Thormählen, Thorsten; Seidel, Hans-Peter
Language:English
Publisher:Springer
Place of Publication:Heidelberg, Germany
Date of Publication (YYYY-MM-DD):2009
Title of Proceedings:International Conference on Image Analysis and Recognition (ICIAR 2009)
Start Page:258
End Page:267
Title of Series:Lecture Notes in Computer Science
Place of Conference/Meeting:Halifax, Canada
(Start) Date of Conference/Meeting
 (YYYY-MM-DD):
2009-07-06
End Date of Conference/Meeting 
 (YYYY-MM-DD):
2009-07-08
Audience:Experts Only
Intended Educational Use:No
Abstract / Description:The SIFT (Scale Invariant Feature Transform) descriptor is a widely used method
for matching image features. However, perfect scale invariance can not be
achieved in practice because of sampling artefacts, noise in the image data,
and the fact that the computational effort limits the number of analyzed scale
space images. In this paper we propose a modification of the descriptor's
regular grid of orientation histogram bins to an irregular grid. The irregular
grid approach reduces the negative effect of scale error and significantly
increases the matching precision for image features. Results with a standard
data set are presented that show that the irregular grid approach outperforms
the original SIFT descriptor and other state-of-the-art extentions.
Last Change of the Resource (YYYY-MM-DD):2010-01-12
External Publication Status:published
Document Type:Conference-Paper
Communicated by:Hans-Peter Seidel
Affiliations:MPI für Informatik/Computer Graphics Group
Identifiers:LOCALID:C125675300671F7B-68A3510DE982DAE9C1257583004A992D-...
URL:http://www.mpi-inf.mpg.de/~hasler/download/CuiHasT...
DOI:10.1007/978-3-642-02611-9_26
The scope and number of records on eDoc is subject to the collection policies defined by each institute - see "info" button in the collection browse view.