DocumentCode
3630471
Title
Affine moment invariants generated by automated solution of the equations
Author
Tomas Suk;Jan Flusser
Author_Institution
Institute of Information Theory and Automation of the ASCR, Pod vod?renskou v?.?? 4, 182 08 Praha 8, Czech Republic
fYear
2008
Firstpage
1
Lastpage
4
Abstract
Pattern recognition of objects on affinely distorted images based on moments is important task researched for many years. Affine moment invariants are significant tool for it. They can be generated by a few methods. Automated direct solution of the Cayley-Aronhold differential equation has not been referred yet. It makes possible to generate invariants with much higher weights than other methods, but we must pay more attention to the numerical stability of the computation. The method is demonstrated on examples.
Keywords
"Transforms","Mirrors","Reflection","Differential equations","Information theory","Automation","Pattern recognition","Numerical stability","Jacobian matrices","Polynomials"
Publisher
ieee
Conference_Titel
Pattern Recognition, 2008. ICPR 2008. 19th International Conference on
ISSN
1051-4651
Print_ISBN
978-1-4244-2174-9
Type
conf
DOI
10.1109/ICPR.2008.4761221
Filename
4761221
Link To Document