Smile Detectors

LAUD12 and TAUD12 are  respectively the implementations of our LBP and LPQ-TOP-based AU12 (smile) detectors. They are developed as stand-alone WIN32 executables.

The models are trained on the MMI database. The input can either be a video sequence (.avi) or a set of images that form a video (.png). The systems assume that the image/video contains a frontal view of the face and that the video frame rate is 25 fps. Resampling will be required for videos with a different frame rate. The detectors output .csv files with their predictions for each frame (1 for active, -1 otherwise) and save them in the same directory as that containing the images or the video.

Note that TAUD12 is unable to detect a smile in the first and last couple of frames (the descriptors used are window-based, so for example when the window is of 11 frames it will not be possible to detect the activation of the AU for the first and last 5 frames). This is a first version of the software, further versions are expected in the near future.

More information about these detectors can be found in:
Bihan Jiang, Michel F. Valstar, and Maja Pantic, ‘Action Unit detection using sparse appearance descriptors in space-time video volumes’, IEEE Int’l. Conf. Face and Gesture Recognition (FG’11), March 2011.

We kindly request that you cite this work if you decide to use this tool for research purposes.

LAUD12 can be downloaded below. This tool is compiled using Microsoft visual studio 2010. If you do not have Visual Studio 2010 installed, you may need to install the Microsoft visual C++ 2010 Runtime in order to run the executable provided here:


To detect AU12 in a single image/image directory/video

LAUD12 C:\tmp\img0001.png -f -v

LAUD12 C:\tmp\testDirectory\ -f -d -v 

LAUD12 C:\tmp\testVideo.avi  -f -V -v   

Call LAUD without input arguments to see usage options. 


TAUD12 can be downloaded below. Note that this version of the code is compiled using Microsoft Visual Studio 2010 and MATLAB 2012a. If you don't have MATLAB 2012a, please install the MCR Installer version 7.17. If you don't have VS2010, please install the Microsoft Visual C++ 2010 Runtime library:

To detect AU12 in an image directory/video:

TAUD12 C:\tmp\testDirectory\

TAUD12 C:\tmp\testVideo.avi