Face morphing

1. BY
B .Srikanth
08Q61A0562
Department
Of
Computer Science
AVANTHI INSTITUTE OF ENGINEERING & TECHNOLOGY
Face-Morphing

2. Introduction
“Morphing” is an interpolation technique used to
create a series of intermediate objects from two
objects.
“The face-morphing” automatically extracts feature
points on the face and morphing is performed.
This was proposed by Mr. M.Biesel within Bayesian
framework to do automatic face morphing.

3. Outline of the face-morphing

4. Pre – Processing
removing the noisy backgrounds

clipping to get a proper facial image, and

scaling the image to a reasonable size.

5. Feature Finding
We first compute the complexity map
we multiply the complexity map by a weighting function.
we find the three highest peaks in the weighted complexity
map .
Finally, the similarity is measured in the correlation-coefficient
sense
Here we find 4 major feature points, namely the two eyes,
and the two end-points of the mouth.

6. Feature Finding

7. Image Partitioning
Feature finder can gives the positions of the eyes and the
end points of the mouth, so we get 4 feature points.
We generate 6 more feature points around the face edge.
__________

Contd….

8. Based on these 10 feature points, 16 non-overlapping
triangular or quadrangular regions developed

As the feature points are at different positions, we do
warping between images.
Image1 Image2
Image Partitioning

9. Coordinate Transformations
Affine Transformation
D
A
B
C E
F
p
q

10. Coordinate Transformations
Bilinear Transformation

11. Cross-Dissolving
The last phase of face - morphing
Cross-dissolving is described by the following
equation,
where A,B are the pair of images, and C is the
morphing result.

12. Example on typical morphing process.
__________


Pre - Processing
Coordinate
transformations
__________
Cross-dissolve

13. Morphing between faces of different
people
- human and animal (lion)
- man and man

14. Morphing between different images of
the same person
Serious <=== ===> Smiling

15. Conclusion
We believe that feature extraction is the key
technique for automatic face morphing.
More and more feature points give the better result

Therefore, in this presentation we emphasized on
eye-finder.
This method, is successful in eye detection rate by
84%.

16. References
Martin Bichsel, "Automatic Interpolation and
Recognition of Face Images by Morphing”.
Jonas Gomes, "Warping and morphing of
graphical objects", Morgan Kaufmann
Publishers (1999).