DocumentCode :
178150
Title :
Affine Alignment of Occluded Shapes
Author :
Santa, Zsolt ; KATO, ZOLTAN
Author_Institution :
Image Process. & Comput. Graphics Dept., Univ. of Szeged, Szeged, Hungary
fYear :
2014
fDate :
24-28 Aug. 2014
Firstpage :
2155
Lastpage :
2160
Abstract :
A novel affine registration technique is proposed which efficiently handles the partial occlusion problem. The proposed method is working without point wise correspondences or radiometric information´s. The aligning transformation is found by solving a system of non-linear equations and minimizing the area of occlusions. Each equation is generated by integrating a non-linear function over the foreground domains of the shapes. In order to deal with occlusions, the shapes are approximated by polygons and the occluded areas are determined with simple boolean operators. Based on the tests on a large synthetic dataset, the proposed approach outperforms state of the art algorithms.
Keywords :
image registration; nonlinear equations; nonlinear functions; affine alignment; affine registration technique; aligning transformation; large synthetic dataset; nonlinear equations; nonlinear function; occluded shapes; partial occlusion problem; Approximation algorithms; Approximation methods; Equations; Mathematical model; Minimization; Robustness; Shape;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2014 22nd International Conference on
Conference_Location :
Stockholm
ISSN :
1051-4651
Type :
conf
DOI :
10.1109/ICPR.2014.375
Filename :
6977087
Link To Document :
بازگشت