Generalized affine moment invariants for object recogn

Author

Rahtu, Esa ; Salo, Mikko ; Heikkila, Janne ; Flusser, Jan

Author_Institution

Dep. of Electr. & Inf. Eng., Oulu Univ.

Volume

2

fYear

0

fDate

0-0 0

Firstpage

634

Lastpage

637

Abstract

This paper introduces a new way of extracting affine invariant features from image functions. The presented approach is based on combining affine moment invariants (AMI) with multiscale invariants, in particular multiscale auto convolution (MSA) and spatial multiscale affine invariants (SMA). Our approach includes all of these invariants as special cases, but also makes it possible to construct new ones. According to the performed experiments the introduced features provide discriminating information for affine invariant object classification, clearly outperforming standard AMI, MSA, and SMA

Keywords

feature extraction; object recognition; affine invariant feature extraction; affine invariant object classification; generalized affine moment invariants; image functions; multiscale auto convolution; multiscale invariants; object recognition; spatial multiscale affine invariants; Ambient intelligence; Automation; Data mining; Feature extraction; Image recognition; Image segmentation; Information theory; Machine vision; Object recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.599

Filename

1699285