Upcoming SlideShare
×

# Face morphing

3,674 views

Published on

Published in: Technology, Art & Photos
1 Like
Statistics
Notes
• Full Name
Comment goes here.

Are you sure you want to Yes No
• Be the first to comment

Views
Total views
3,674
On SlideShare
0
From Embeds
0
Number of Embeds
2
Actions
Shares
0
215
0
Likes
1
Embeds 0
No embeds

No notes for slide

### Face morphing

1. 1. Face-Morphing BY B .Srikanth 08Q61A0562 Department Of Computer Science AVANTHI INSTITUTE OF ENGINEERING & TECHNOLOGY
2. 2. Introduction <ul><li>“ Morphing ” is an interpolation technique used to create a series of intermediate objects from two objects. </li></ul><ul><li>“ The face-morphing ” automatically extracts feature points on the face and morphing is performed. </li></ul><ul><li>This was proposed by Mr. M.Biesel within Bayesian framework to do automatic face morphing. </li></ul>
3. 3. Outline of the face-morphing
4. 4. Pre – Processing <ul><li>removing the noisy backgrounds </li></ul><ul><li>clipping to get a proper facial image, and </li></ul><ul><li>scaling the image to a reasonable size.  </li></ul>
5. 5. Feature Finding <ul><li>We first compute the complexity map </li></ul><ul><li>we multiply the complexity map by a weighting function. </li></ul><ul><li>we find the three highest peaks in the weighted complexity map . </li></ul><ul><li>Finally, the similarity is measured in the correlation-coefficient sense </li></ul><ul><li>Here we find 4 major feature points, namely the two eyes, and the two end-points of the mouth. </li></ul>
6. 6. Feature Finding
7. 7. Image Partitioning <ul><li>Feature finder can gives the positions of the eyes and the end points of the mouth, so we get 4 feature points. </li></ul><ul><li>We generate 6 more feature points around the face edge.  </li></ul>__________ Contd….
8. 8. <ul><li>Based on these 10 feature points, 16 non-overlapping triangular or quadrangular regions developed </li></ul><ul><li>As the feature points are at different positions, we do warping between images. </li></ul>Image Partitioning Image1 Image2
9. 9. Coordinate Transformations <ul><li>Affine Transformation </li></ul>D A B C E F p q
10. 10. Coordinate Transformations <ul><li>Bilinear Transformation </li></ul>
11. 11. Cross-Dissolving <ul><li>The last phase of face - morphing </li></ul><ul><li>Cross-dissolving is described by the following equation, </li></ul>where A,B are the pair of images, and C is the morphing result.
12. 12. Example on typical morphing process. __________   Pre - Processing Coordinate transformations __________ Cross-dissolve
13. 13. Morphing between faces of different people <ul><li>- human and animal (lion) </li></ul>- man and man
14. 14. Morphing between different images of the same person      Serious <===                                                   ===>   Smiling
15. 15. Conclusion <ul><li>We believe that feature extraction is the key technique for automatic face morphing. </li></ul><ul><li>More and more feature points give the better result </li></ul><ul><li>Therefore, in this presentation we emphasized on eye-finder. </li></ul><ul><li>This method, is successful in eye detection rate by 84%. </li></ul>
16. 16. References <ul><li>Martin Bichsel, &quot;Automatic Interpolation and Recognition of Face Images by Morphing”. </li></ul><ul><li>Jonas Gomes, &quot;Warping and morphing of graphical objects&quot;, Morgan Kaufmann Publishers (1999). </li></ul>
17. 17. Queries? ? ? ? ? ? ? ? ? ? ? ? Thank You