DocumentCode :
3490141
Title :
Affine alignment of compound objects: A direct approach
Author :
Domokos, Csaba ; Kato, Zoltan
Author_Institution :
Image Process. & Comput. Graphics Dept., Univ. of Szeged, Szeged, Hungary
fYear :
2009
fDate :
7-10 Nov. 2009
Firstpage :
169
Lastpage :
172
Abstract :
A direct approach for parametric estimation of 2D affine deformations between compound shapes is proposed. It provides the result as a least-square solution of a linear system of equations. The basic idea is to fit Gaussian densities over the objects yielding covariant functions, which preserves the effect of the unknown transformation. Based on these functions, linear equations are constructed by integrating nonlinear functions over appropriate domains. The main advantages are: linear complexity, easy implementation, works without any time consuming optimization or established correspondences. Comparative tests show that it outperforms state-of-the-art methods both in terms of precision, robustness and complexity.
Keywords :
Gaussian processes; affine transforms; image recognition; least squares approximations; nonlinear functions; optimisation; shape recognition; 2D affine deformations; Gaussian densities; compound objects affine alignment; compound shapes; integrating nonlinear functions; least square solution; linear complexity; linear system; objects yielding covariant functions; parametric estimation; state-of-the-art methods; time consuming optimization; Computer graphics; Gaussian distribution; Image processing; Linear systems; Nonlinear distortion; Nonlinear equations; Parameter estimation; Robustness; Shape; Testing; Affine registration; Compound shape; Gaussian distribution; Mahalanobis distance;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
ISSN :
1522-4880
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2009.5414195
Filename :
5414195
Link To Document :
بازگشت