A fully affine invariant image comparison method

Author

Yu, Guoshen ; Morel, Jean-Michel

Author_Institution

CMAP, Ecole Polytech., Palaiseau

fYear

2009

fDate

19-24 April 2009

Firstpage

1597

Lastpage

1600

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).

Keywords

affine transforms; image matching; affine invariant image comparison method; image matching; scale invariance; Cameras; Costs; Deformable models; Detectors; Distortion measurement; Ear; Equations; Image edge detection; Image matching; Optical distortion; SIFT; affine invariance; affine normalization; image matching; scale invariance;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on

Conference_Location

Taipei

ISSN

1520-6149

Print_ISBN

978-1-4244-2353-8

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2009.4959904

Filename

4959904