Discover MakerZone

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi

Learn more

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

Thread Subject:
active appearance models

Subject: active appearance models

From: Vinod

Date: 18 Dec, 2009 15:23:02

Message: 1 of 1

Hello Friends,

I am developing AAMs for faces. I have been going through the works of Tim Cootes and others. I have done the initial work of aligning the images using procrustes transform and also found out the mean.

I am a bit confused in modelling shape variations. For this basically I shall need to follow the steps below-
1) Compute the mean(¹x).
2) Compute the covariance of the data set. Covariance is S
3)Compute the eigenvectors,and corresponding eigenvalues of S.
4)If eigenvectors contains the 't' eigenvectors corresponding to the largest eigenvalues, then we can then approximate any of the training set, 'x' using the relation x = ¹x + eigenvectors*b.The vector b de¯nes a set of parameters of a deformable model.

This 'B' is what I am stuck with . Could you please explain or even hint me on how I can get this ?

please refer page 17 of this document

http://www.face-rec.org/algorithms/AAM/app_models.pdf

Thanks and Regards,
Vinod Karuvat.

Tags for this Thread

No tags are associated with this thread.

What are tags?

A tag is like a keyword or category label associated with each thread. Tags make it easier for you to find threads of interest.

Anyone can tag a thread. Tags are public and visible to everyone.

Contact us