LAUD

LAUD is the implementation of our LBP-based AU detector, desribed in this paper. It is developed by me as a standalone, WIN32 command-line version of the AU detector implemented in the SEMAINE project. It comes with trained models for the following AUs: AU1, AU2, AU$, AU5, AU6, AU7, AU9, AU12, AU14, AU15, AU20, AU25, AU27, and AU45. Not all of these are equally good though. AU1, AU2, AU4, AU12, and AU25 were deemed good enough to be used in SEMAINE, but I will let you draw your own conclusions. The system assumes that the image is already frontal. If you pass the -f argument, it will do face detection but not registration. If people are interested, I may integrate a simple in-plane head registration method that we also use in the SEMAINE system.

How to use it: Detect AU 1 in a single image:

LAUD 1 C:\tmp\img0001.png -v -f

or in all images in a directory:

LAUD 1 C:\tmp\imdir\ -v -f -d

Call LAUD without input arguments to see all input options. If you process a whole directory, the results will be stored in that directory.

Download the MSI installer

BoRMaN

The BoRMaN programme detects 20 fiducial facial points. Instead of scanning an image or image region for the location of a facial point, it can use every location in a point's neighbourhood to predict where the target point is relative to that location. This considerable speeds up point detection. In only a few iterations the facial point can be found. Markov networks are used to confirm whether a set of predicted facial points adhere to shape statistics, and if they don't the Markov nets suggest new locations to continue the search for the facial point.

More information about the point detector can be found in:

Michel F. Valstar, Brais Martinez, Xavier Binefa, and Maja Pantic 'Facial Point Detection using Boosted Regression and Graph Models', IEEE Int'l Conf. Computer Vision and Pattern Recognition, pp. 2729-2736, San Francisco, USA, June 2010

We kindly request you to cite this work if you decide to use the point detector for research purposes.

The BoRMaN detector is provided as compiled matlab code. Download the link below, and execute the downloaded file to install the required Matlab Runtime Component. Follow the instructions in the README.txt for more installation and usage instructions.

iBUG software download site