Face morphing

17
BY B .Srikanth 08Q61A0562 Department Of Computer Science AVANTHI INSTITUTE OF ENGINEERING & TECHNOLOGY Face-Morphing

description

 

Transcript of Face morphing

Page 1: Face morphing

BY

B .Srikanth08Q61A0562

Department

Of

Computer Science

AVANTHI INSTITUTE OF ENGINEERING & TECHNOLOGY

Face-Morphing

Page 2: Face morphing

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.

Page 3: Face morphing

Outline of the face-morphing

Page 4: Face morphing

Pre – Processing

removing the noisy backgrounds

clipping to get a proper facial image, and

scaling the image to a reasonable size. 

Page 5: Face morphing

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.

Page 6: Face morphing

Feature Finding

Page 7: Face morphing

Image PartitioningFeature 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….

Page 8: Face morphing

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

Page 9: Face morphing

Coordinate TransformationsAffine Transformation

DA

B

C EF

pq

Page 10: Face morphing

Coordinate TransformationsBilinear Transformation

Page 11: Face morphing

Cross-DissolvingThe 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.

Page 12: Face morphing

Example on typical morphing process.

__________

 

Pre - Processing

Coordinate transformations

__________

Cross-dissolve

Page 13: Face morphing

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

- man and man

Page 14: Face morphing

Morphing between different images of the same person

     Serious <===                                                   ===>   Smiling

Page 15: Face morphing

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%.

Page 16: Face morphing

References

Martin Bichsel, "Automatic Interpolation and Recognition of Face Images by Morphing”.

Jonas Gomes, "Warping and morphing of graphical objects", Morgan Kaufmann Publishers (1999).

Page 17: Face morphing