The breif procedure for doing the Morphing was
as follows -
1. The source and the destination images were read.
2. Feature points were interactively marked on both
the images.
3. This 'node map' was then triangulated using De
Launay Triangulation.
4. Each triangle was taken one by one, its vertices
and theri intensities were linearly intepolated to the intermediate frames.
5. The triangles were scan converted, and intensities
of the points inside the triangle were obtained by an inverse mapping
using Brycentric Coordinates.
6. All the frames were joined togther to form the
animations shown here.
The various results obtained are shown below -
1. We are the World (My favourite)
|
|
|
|
|
|
|
|
|
|
|
faces morphed in a sequence. Each sequence has 10 frames. |
2. From the Earth to the Moon
|
|
|
|
3. A very sharp buisiness man
|
|
|
4. A Parisian night in London !!
|
|
|
Salient Features of this Implementation :
1. A blazing fast DeLaunay Triangulator courtesy Jonathan
Richard Shewchuk, UCB, Berkley California. His Triangle and Showme
utilities
have been very helpful in this work.
They can be downloaded from Netlib.
2. Very Interactive - allows the user to vary a lot
of parameters at runtime such as -
a) Interactive marking of Feature
points through a Java program
b) Ability to resuse old 'Node
Maps' and 'Triangulations' if present.
b) Ability to apply Median Filtering
to each individual frame to remove 'holes' if they appear.
c) Auto-Normalization of destination
image sizes if it of a size different from the source.
d) Auto-generation of frame names
so that they can be easily combined into animation sequences using the
ImageMagick Convert Tool.
e) Auto-Marking of eight bounding
points for the source/detination images so that it doesn't have to be done
by the user.
Improvements Possible -
1. Use of Bilinear Interpolation instead of simple
truncation to get a better morph when extreme deformations are involved.
2. Use of a Feature-Line based algorithm which may
be computationally less intensive and produce better morphs.
3. I have used a very rudimentary approach for scan
conversion which is good enough for small images, a better optimized scan
conversion would be however more efficient.
Page last updated on 28 January, 2004. | AT cse.iitd.ac.in | © Parag Chaudhuri , 2009 |