A fully affine invariant image comparison method

Guoshen YU; Jean-Michel MOREL

doi:10.1109/ICASSP.2009.4959904

A fully affine invariant image comparison method

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

156 Citations (Scopus)

Abstract

A fully affine invariant image comparison method, Affine-SIFT (ASIFT) is introduced. While SIFT is fully invariant with respect to only four parameters namely zoom, rotation and translation, the new method treats the two left over parameters : the angles defining the camera axis orientation. Against any prognosis, simulating all views depending on these two parameters is feasible. The method permits to reliably identify features that have undergone very large affine distortions measured by a new parameter, the transition tilt. State-of-the-art methods hardly exceed transition tilts of 2 (SIFT), 2.5 (Harris-Affine and Hessian-Affine) and 10 (MSER). ASIFT can handle transition tilts up 36 and higher (see Fig. 1). ©2009 IEEE.

Original language	English
Title of host publication	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings, ICASSP 2009
Publisher	IEEE
Pages	1597-1600
Number of pages	4
ISBN (Print)	9781424423538
DOIs	https://doi.org/10.1109/ICASSP.2009.4959904
Publication status	Published - 2009
Externally published	Yes
Event	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Taipei, Taiwan, China Duration: 19 Apr 2009 → 24 Apr 2009

Conference

Conference	2009 IEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated title	ICASSP 2009
Country/Territory	Taiwan, China
City	Taipei
Period	19/04/09 → 24/04/09

Keywords

Affine invariance
Affine normalization
Image matching
Scale invariance
SIFT

Access to Document

10.1109/ICASSP.2009.4959904

Cite this

@inproceedings{9c942a22de7040dc9ecba3725faab8fc,

title = "A fully affine invariant image comparison method",

abstract = "A fully affine invariant image comparison method, Affine-SIFT (ASIFT) is introduced. While SIFT is fully invariant with respect to only four parameters namely zoom, rotation and translation, the new method treats the two left over parameters : the angles defining the camera axis orientation. Against any prognosis, simulating all views depending on these two parameters is feasible. The method permits to reliably identify features that have undergone very large affine distortions measured by a new parameter, the transition tilt. State-of-the-art methods hardly exceed transition tilts of 2 (SIFT), 2.5 (Harris-Affine and Hessian-Affine) and 10 (MSER). ASIFT can handle transition tilts up 36 and higher (see Fig. 1). {\textcopyright}2009 IEEE.",

keywords = "Affine invariance, Affine normalization, Image matching, Scale invariance, SIFT",

author = "Guoshen YU and Jean-Michel MOREL",

year = "2009",

doi = "10.1109/ICASSP.2009.4959904",

language = "English",

isbn = "9781424423538",

pages = "1597--1600",

booktitle = "2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings, ICASSP 2009",

publisher = "IEEE",

note = "2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 ; Conference date: 19-04-2009 Through 24-04-2009",

}

YU, G & MOREL, J-M 2009, A fully affine invariant image comparison method. in 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings, ICASSP 2009., 4959904, IEEE, pp. 1597-1600, 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, Taipei, Taiwan, China, 19/04/09. https://doi.org/10.1109/ICASSP.2009.4959904

TY - GEN

T1 - A fully affine invariant image comparison method

AU - YU, Guoshen

AU - MOREL, Jean-Michel

PY - 2009

Y1 - 2009

N2 - A fully affine invariant image comparison method, Affine-SIFT (ASIFT) is introduced. While SIFT is fully invariant with respect to only four parameters namely zoom, rotation and translation, the new method treats the two left over parameters : the angles defining the camera axis orientation. Against any prognosis, simulating all views depending on these two parameters is feasible. The method permits to reliably identify features that have undergone very large affine distortions measured by a new parameter, the transition tilt. State-of-the-art methods hardly exceed transition tilts of 2 (SIFT), 2.5 (Harris-Affine and Hessian-Affine) and 10 (MSER). ASIFT can handle transition tilts up 36 and higher (see Fig. 1). ©2009 IEEE.

AB - A fully affine invariant image comparison method, Affine-SIFT (ASIFT) is introduced. While SIFT is fully invariant with respect to only four parameters namely zoom, rotation and translation, the new method treats the two left over parameters : the angles defining the camera axis orientation. Against any prognosis, simulating all views depending on these two parameters is feasible. The method permits to reliably identify features that have undergone very large affine distortions measured by a new parameter, the transition tilt. State-of-the-art methods hardly exceed transition tilts of 2 (SIFT), 2.5 (Harris-Affine and Hessian-Affine) and 10 (MSER). ASIFT can handle transition tilts up 36 and higher (see Fig. 1). ©2009 IEEE.

KW - Affine invariance

KW - Affine normalization

KW - Image matching

KW - Scale invariance

KW - SIFT

UR - https://www.scopus.com/pages/publications/70349383390

U2 - 10.1109/ICASSP.2009.4959904

DO - 10.1109/ICASSP.2009.4959904

M3 - Conference paper (refereed)

AN - SCOPUS:70349383390

SN - 9781424423538

SP - 1597

EP - 1600

BT - 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, Proceedings, ICASSP 2009

PB - IEEE

T2 - 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing

Y2 - 19 April 2009 through 24 April 2009

ER -

A fully affine invariant image comparison method

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this