Image Mosaicking Through Macro-Feature Affine Matching

Author

Lucchese, Luca ; Leorin, Simone ; Cortelazzo, Guido M.

Author_Institution

Sch. of Electr. Eng. & Comput. Sci., Oregon State Univ., Corvallis, OR

fYear

2005

fDate

Oct. 30 2005-Nov. 2 2005

Firstpage

1

Lastpage

4

Abstract

This paper presents a new method for registering images related by 2-D affine transformations. The method is based on extracting macro-features from the images to register and matching the polar curves associated with their energies, defined as the squared Fourier transform magnitudes. Such matching is formulated as a simple minimization problem whose optimal solution if found with the Levenberg-Marquardt algorithm. The excellent performance of the algorithm is shown through a practical example of image mosaicking

Keywords

Fourier transforms; affine transforms; feature extraction; image matching; image registration; image segmentation; 2-D affine transformation; Levenberg-Marquardt algorithm; image matching; image mosaicking; image registration; macro-feature extraction; minimization problem; polar curves; squared Fourier transform magnitude; Computer science; Data mining; Feature extraction; Fourier transforms; Image processing; Image registration; Image segmentation; Minimization methods; Motion estimation; Shape;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Signal Processing, 2005 IEEE 7th Workshop on

Conference_Location

Shanghai

Print_ISBN

0-7803-9288-4

Electronic_ISBN

0-7803-9289-2

Type

conf

DOI

10.1109/MMSP.2005.248650

Filename

4014071