DocumentCode
2530758
Title
Projective registration with difference decomposition
Author
Gleicher, Michael
Author_Institution
Apple Res. Labs., Cupertino, CA, USA
fYear
1997
fDate
17-19 Jun 1997
Firstpage
331
Lastpage
337
Abstract
Current methods for registering image regions perform well for simple transformations or large image regions. The author presents a new method that is better able to handle small image regions as they deform with nonlinear transformations. He introduces difference decomposition, a novel approach to solving the registration problem. The method is a generalization of previous methods and can better handle nonlinear transforms. Although the methods are general, he focuses on projective transformations and introduces piecewise-projective transformations for modeling the motions of non-planar objects. He concludes with examples from a prototype implementation
Keywords
computer vision; image registration; image segmentation; motion estimation; performance evaluation; difference decomposition; image region registration; image transformations; nonlinear transformations; nonplanar object motion modeling; performance; piecewise-projective transformations; projective registration; prototype implementation; Application software; Computer errors; Computer graphics; Computer vision; Image coding; Image recognition; Laboratories; Prototypes; Surveillance; Target tracking;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on
Conference_Location
San Juan
ISSN
1063-6919
Print_ISBN
0-8186-7822-4
Type
conf
DOI
10.1109/CVPR.1997.609345
Filename
609345
Link To Document