Share Email Print

Optical Engineering

Contour-based image registration with local deformations
Author(s): Wen-Nung Lie; Cheng H. Chuang
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This research is focused on the study of local-type image registration techniques, which concern pixel mapping between two correlated images with both global and local deformations. Our algorithm is object-contour-based, meaning that control points that conduct the transformation are adaptively selected from the matched contour points. It is novel in two important respects. First, we propose to match object contours in the source and target images by using locally-maximal-curvature points and curve projection. Second, the selection of control points is capable of adapting to both global and local deformations, normally being denser in contour segments with substantial local deformations. The proposed scheme is also hybrid in the sense that local contour matching and global surface-spline fitting of control points are combined. Simulations and some comparisons are made by using infrared thermographs and ordinary gray images. Experiments show better registration accuracy of object contours than with traditional methods such as elastic or curvature scale space matching.

Paper Details

Date Published: 1 May 2003
PDF: 12 pages
Opt. Eng. 42(5) doi: 10.1117/1.1564099
Published in: Optical Engineering Volume 42, Issue 5
Show Author Affiliations
Wen-Nung Lie, National Chung Cheng Univ. (Taiwan)
Cheng H. Chuang, National Chung Cheng Univ. (Taiwan)

© SPIE. Terms of Use
Back to Top