Title :
Adaptive Registration of Very Large Images
Author :
Jackson, Brian P. ; Goshtasby, A. Ardeshir
Author_Institution :
Comput. Sci. & Eng. Dept., Wright State Univ., Dayton, OH, USA
Abstract :
The main difficulty in image registration is in determining the geometric difference between the given images. An image registration method is introduced that determines the geometric difference between two images in a coarse-to-fine fashion. The global transformation needed to register the images is defined in terms of a collection of local transformations, each describing the geometric difference between corresponding local neighborhoods in the images. Preliminary experimental results of the proposed method are presented and discussed.
Keywords :
image registration; adaptive image registration method; geometric difference; global transformation; local transformations; very large images; Approximation methods; Complexity theory; Equations; Geometry; Image registration; Image resolution; Registers; adaptive registration; big image; hierarchical registration; image registration;
Conference_Titel :
Computer Vision and Pattern Recognition Workshops (CVPRW), 2014 IEEE Conference on
Conference_Location :
Columbus, OH
DOI :
10.1109/CVPRW.2014.58