This software uses the projective transformation to register images of a flat scene obtained from different
views. The registration is fully automatic and the user only provides the names of the two images to be
registered. The program will then register the images and display the result. The registration process involves
selecting a set of landmarks in each image, determining the correspondence between them, and determining
the transformation parameters from the correspondences .
Assumptions: It is assumed that
If one or more of these assumptions are violated, the program may register the images approximately, or
report a failure.
Modes of operation: The program operates at three different modes.
views. The registration is fully automatic and the user only provides the names of the two images to be
registered. The program will then register the images and display the result. The registration process involves
selecting a set of landmarks in each image, determining the correspondence between them, and determining
the transformation parameters from the correspondences .
Assumptions: It is assumed that
- the imaged scene is rather flat
- the images are in the same modality,
- at least 50% overlap exists between the images.
If one or more of these assumptions are violated, the program may register the images approximately, or
report a failure.
Modes of operation: The program operates at three different modes.
- Default mode: This is a fast initial mode used to register the images quickly. For some images, this is
sufficient. - Redo mode: For images with considerable intensity differences, it may be necessary to redo the
registration using a larger number of landmarks. The user presses a Redo button after viewing the
registration result of the default mode. - Refinement mode: In this mode, the positions of the landmarks are more accurately determined by
template matching and the registration is repeated. Examples of image registration by this software are
given below.
(a)
(b)
(c)
(d)
Fig. 1. (a), (b) Two images of a quilt on a wall from slightly different views. (c) Registration using the default
mode. This takes about fifteen seconds. (d) Refinement of the registration. This takes several seconds.
mode. This takes about fifteen seconds. (d) Refinement of the registration. This takes several seconds.
(a)
(b)
(c)
(d)
Fig. 2. (a), (b) Two slightly different views of the Diamond Head area, Hawaii. (c) Initial registration. (d)
Refined registration. Note the difference between the images in the lower right corner due to the view-angle
difference between the images. The program is robust under outliers, using similar image features and
ignoring dissimilar features when registering the images.
Refined registration. Note the difference between the images in the lower right corner due to the view-angle
difference between the images. The program is robust under outliers, using similar image features and
ignoring dissimilar features when registering the images.
(a)
(b)
(c)
Fig. 3. (a), (b) Two images of a flower garden. (c) Registration of the images by the projective transformation.
Although the scene is not completely flat, compared to the distance of the camera to the scene, the changes in
scene elevation are small. The images have been obtained from about the same viewpoint.
Although the scene is not completely flat, compared to the distance of the camera to the scene, the changes in
scene elevation are small. The images have been obtained from about the same viewpoint.
To obtain a license for this registration software, place an order here =>
 |  |
| 2-D auto projective registration |
| Image Fusion Systems Research |