Proceedings Article, Paper
@InProceedings
Beitrag in Tagungsband, Workshop


Show entries of:

this year (2019) | last year (2018) | two years ago (2017) | Notes URL

Action:

login to update

Options:




Library Locked Library locked




Author, Editor

Author(s):

Cui, Yan
Hasler, Nils
Thormählen, Thorsten
Seidel, Hans-Peter

dblp
dblp
dblp
dblp

Not MPG Author(s):

Cui, Yan

Editor(s):

Kamel, Mohamed
Campilho, Aurélio

dblp
dblp

Not MPII Editor(s):

Kamel, Mohamed
Campilho, Aurélio

BibTeX cite key*:

CuiHasThoSei09

Title, Booktitle

Title*:

Scale Invariant Feature Transform with Irregular Orientation Histogram Binning

Booktitle*:

Image Analysis and Recognition : 6th International Conference, ICIAR 2009

Event, URLs

URL of the conference:

http://www.iciar.uwaterloo.ca/iciar09/

URL for downloading the paper:

http://www.mpi-inf.mpg.de/~hasler/download/CuiHasThoSei09igSIFT.pdf

Event Address*:

Halifax, Canada

Language:

English

Event Date*
(no longer used):


Organization:


Event Start Date:

6 July 2009

Event End Date:

8 July 2009

Publisher

Name*:

Springer

URL:

http://www.springer.com/

Address*:

Berlin, Germany

Type:


Vol, No, Year, pp.

Series:

Lecture Notes in Computer Science

Volume:

5627

Number:

-

Month:

July

Pages:

258-267

Year*:

2009

VG Wort Pages:


ISBN/ISSN:

978-3-642-02610-2

Sequence Number:


DOI:

10.1007/978-3-642-02611-9_26



Note, Abstract, ©

Note:

(to appear)

(LaTeX) Abstract:

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.



Download
Access Level:

Public

Correlation

MPG Unit:

Max-Planck-Institut für Informatik



MPG Subunit:

Computer Graphics Group

Appearance:

MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort



BibTeX Entry:

@INPROCEEDINGS{CuiHasThoSei09,
AUTHOR = {Cui, Yan and Hasler, Nils and Thorm{\"a}hlen, Thorsten and Seidel, Hans-Peter},
EDITOR = {Kamel, Mohamed and Campilho, Aur{\'e}lio},
TITLE = {Scale Invariant Feature Transform with Irregular Orientation Histogram Binning},
BOOKTITLE = {Image Analysis and Recognition : 6th International Conference, ICIAR 2009},
PUBLISHER = {Springer},
YEAR = {2009},
NUMBER = {-},
VOLUME = {5627},
PAGES = {258--267},
SERIES = {Lecture Notes in Computer Science},
ADDRESS = {Halifax, Canada},
MONTH = {July},
ISBN = {978-3-642-02610-2},
DOI = {10.1007/978-3-642-02611-9_26},
NOTE = {(to appear)},
}


Entry last modified by Anja Becker, 03/15/2010
Show details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)
Hide details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)

Editor(s)
[Library]
Created
03/24/2009 02:34:48 PM
Revisions
2.
1.
0.

Editor(s)
Anja Becker
Nils Hasler
Nils Hasler

Edit Dates
15.03.2010 14:51:10
01/12/2010 10:25:42 AM
03/24/2009 02:34:48 PM

Show details for Attachment SectionAttachment Section
Hide details for Attachment SectionAttachment Section