Rank: 1510 based on 80 downloads (last 30 days) and 1 file submitted
photo

Luca Vezzaro

E-mail

Personal Profile:

http://lvezzaro.altervista.org

Professional Interests:

 

Watch this Author's files

 

Files Posted by Luca
Updated   File Tags Downloads
(last 30 days)
Comments Rating
29 Feb 2012 Screenshot ICAAM - Inverse compositional Active Appearance Models An implementation of inverse-compositional Active Appearance Models capable of real-time performance Author: Luca Vezzaro active appearance mod..., image processing defo... 80 46
  • 5.0
5.0 | 2 ratings
Comments and Ratings by Luca View all
Updated File Comments Rating
28 Jul 2014 ICAAM - Inverse compositional Active Appearance Models An implementation of inverse-compositional Active Appearance Models capable of real-time performance Author: Luca Vezzaro

Hello,

Annotation files are using cartesian coordinates:

y

^
|
+---> x

Each point is stored as a row:

-------
|x1 y1|
|x2 y2|
.
.
|xn yn|
-------

The code uses matlab convention for image coordinates:

+----> j
|
|
v
i

and are stored in the same way:

-------
|i1 j1|
|i2 j2|
.
.
|in jn|
-------

Check the xy2ij() and ij2xy() functions for converting between the two.

16 Apr 2014 ICAAM - Inverse compositional Active Appearance Models An implementation of inverse-compositional Active Appearance Models capable of real-time performance Author: Luca Vezzaro

@Elaungkumaran:

1. This is creating the annotations variable:

load(sprintf('cootes/%s', training_files(i).name));

Use the build_model_2d_from_files to not be exposed to such intricacies.

2. What do you mean? fit_2d is the function to fit. You need to provide a shape to start the fit. As AAMs don't do face detection you need to first apply a face detection algorithm to detect the approximate location of the face and use that to fit your AAM to the detected face.

21 Jun 2013 ICAAM - Inverse compositional Active Appearance Models An implementation of inverse-compositional Active Appearance Models capable of real-time performance Author: Luca Vezzaro

I'll try to fix the issue, but first I need to get MATLAB 2012b. I'll see what I can do.

21 Jun 2013 ICAAM - Inverse compositional Active Appearance Models An implementation of inverse-compositional Active Appearance Models capable of real-time performance Author: Luca Vezzaro

Please use a older MATLAB version, if you can.

17 Jun 2013 ICAAM - Inverse compositional Active Appearance Models An implementation of inverse-compositional Active Appearance Models capable of real-time performance Author: Luca Vezzaro

Anika, do you mean Matlab R2011b?

Are you sure you're using the latest version from here? http://sourceforge.net/projects/icaam/files/

Comments and Ratings on Luca's Files View all
Updated File Comment by Comments Rating
31 Jul 2014 ICAAM - Inverse compositional Active Appearance Models An implementation of inverse-compositional Active Appearance Models capable of real-time performance Author: Luca Vezzaro Qu, Bingqing

@Luca Vezzaro

Thx! It is quite helpful!

28 Jul 2014 ICAAM - Inverse compositional Active Appearance Models An implementation of inverse-compositional Active Appearance Models capable of real-time performance Author: Luca Vezzaro Vezzaro, Luca

Hello,

Annotation files are using cartesian coordinates:

y

^
|
+---> x

Each point is stored as a row:

-------
|x1 y1|
|x2 y2|
.
.
|xn yn|
-------

The code uses matlab convention for image coordinates:

+----> j
|
|
v
i

and are stored in the same way:

-------
|i1 j1|
|i2 j2|
.
.
|in jn|
-------

Check the xy2ij() and ij2xy() functions for converting between the two.

28 Jul 2014 ICAAM - Inverse compositional Active Appearance Models An implementation of inverse-compositional Active Appearance Models capable of real-time performance Author: Luca Vezzaro Qu, Bingqing

Hi, Luca

Thanks for your sharing.

All the code are running correctly on my computer. Just got some logic questions.

Did you train the model that all coordinates related to shapes are in inverse order? shape = [Y X] as example.

Many thanks!
Bingqing

22 Apr 2014 ICAAM - Inverse compositional Active Appearance Models An implementation of inverse-compositional Active Appearance Models capable of real-time performance Author: Luca Vezzaro Elangkumaran

I've generated an initial shape. But the AAM still keeps diverging.

Please find more details at: http://goo.gl/1VI131

16 Apr 2014 ICAAM - Inverse compositional Active Appearance Models An implementation of inverse-compositional Active Appearance Models capable of real-time performance Author: Luca Vezzaro Vezzaro, Luca

@Elaungkumaran:

1. This is creating the annotations variable:

load(sprintf('cootes/%s', training_files(i).name));

Use the build_model_2d_from_files to not be exposed to such intricacies.

2. What do you mean? fit_2d is the function to fit. You need to provide a shape to start the fit. As AAMs don't do face detection you need to first apply a face detection algorithm to detect the approximate location of the face and use that to fit your AAM to the detected face.

Contact us