An invariant local vector for content-based image retrieval

Author

Bigorgne, Erwan ; Achard, Catherine ; Devars, Jean

Author_Institution

Lab. des Instrumentation et Syst., Paris, France

Volume

1

fYear

2000

fDate

2000

Firstpage

1019

Abstract

In this paper, we present the use of Full-Zernike moments as a local characterization of the image signal. Their computation allows us to construct a locally invariant vector, of which the projection in an index table provides a vote for some model-image. This approach is based on the quasi-invariant theory applied to perspective transformation. Then it requires a characterization being invariant to translation, rotation and change of scale in the image; in other respect, an appropriate normalization of the signal delivers an invariance to illuminance conditions

Keywords

content-based retrieval; image retrieval; vectors; Full-Zernike moments; content-based image retrieval; image signal; index table; invariant local vector; locally invariant vector; perspective transformation; quasi-invariant theory; rotation invariance; scale invariance; translation invariance; Computer vision; Content based retrieval; Image databases; Image reconstruction; Image retrieval; Indexing; Instruments; Jacobian matrices; Polynomials; Voting;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2000. Proceedings. 15th International Conference on

Conference_Location

Barcelona

ISSN

1051-4651

Print_ISBN

0-7695-0750-6

Type

conf

DOI

10.1109/ICPR.2000.905644

Filename

905644