CS 7321: Computer Vision I
Problem Set 3: Multiresolutions Images and
Splining
http://www.cc.gatech.edu/classes/cs7321_98_winter/ps/PS3.html
Handed Out: Thu February 12, 1998, Due Back: Thu
February 26, 1998 (Before Class)
This problem set will let you play around with multi-resolution techniques
for images.
-
Implement the Adelson and Burt algorithm for splining overlapping images.
The input images can be of any size. This will involve writing programs
to compute the Laplacian pyramid for a given color image and the Gaussian
pyramid for image masks. Implement Expand and Reduce as the basic routines
for constructing the pyramids. You can use a 5x5 kernel with the weights
as given in the paper.
-
Use your program to spline a pair of color images of your choice.
-
Use your program to form a composite images using combinations of images
from http://www-astronomy.mps.ohio-state.edu/~dixie/animals.html
OR
-
Please feel free to gather images from the WWW or collect them via camera
or scanner.
-
For extra credit, compute an additional montage for a sequence of moving
video images.
-
When done, Create an HTML document that gives the matlab program source
code and script saved via the diary command and shows your output images.
-
See /net/www/classes/cs7321_98_winter/u/irfan/ps3/index.html for a generic
template.
-
Your report should be in /net/www/classes/cs7321_98_winter/u/<your-CoC-username>/ps3/index.html
-
In this report
-
Include a one page description of how your program works. Be sure to discuss
the assumptions and weaknesses of the particular technique employed. What
are the limitations of this image splining technique?
-
Include images showing the Gaussian and Laplacian pyramids for one of the
two images.
-
The program source and your output "spliced" images.