NOTE: The following software is provided for research purposes only.
You may not distribute this software in any form without the prior
approval of the University of California.
An implementation of the
contour-based algorithm is now available.
The strategy and explanations can be found in a paper
"A contour-based approach to multisensor image registration",
IEEE Transactions on Image Processing, vol.4, (no.3), pp.320-34, March 1995.
Compiled binaries for SGI, SUN, and IBM/PC can be downloaded.
Some test images are also available. Each archive contains the
contour based registration executables as well as a shell script
for running them (xreg) and a TCL script for a GUI (Register.tcl).
Image registration is concerned with the
establishment of correspondence between images of the same scene. One
challenging problem in this area is the registration of multispectral and
multisensor images. In general, such images have different gray level
characteristics, and simple techniques such as those based on area correlations
cannot be applied directly. On the other hand, contours representing region
boundaries are preserved in most cases. In this paper, we present two
contour-based methods which use region boundaries and other strong edges as
matching primitives. The first contour matching algorithm is based on the
chain-code correlation and other shape similarity criteria such as invariant
moments. Closed contours and the salient segments along the open contours are
matched separately. This method works well for image pairs in which the contour
information is well preserved, such as the optical images from Landsat and Spot
satellites. For the registration of the optical images with synthetic aperture
radar (SAR) images, we propose an elastic contour matching scheme based on the
active contour model. Using the contours from the optical image as the initial
condition, accurate contour locations in the SAR image are obtained by applying
the active contour model. Both contour matching methods are automatic and
computationally quite efficient. Experimental results with various kinds of
image data have verified the robustness of our algorithms, which have
outperformed manual registration in terms of root mean square error at the
The following students contributed to the code
development and/or testing:
David Garza, Yining Deng, and Alan Trombla.
Registration Project Homepage