Multiple kernel learning SVM and statistical validation for facial landmark detection

In this paper we present a robust and accurate method to detect 17 facial landmarks in expressive face images. We introduce a new multi-resolution framework based on the recent multiple kernel algorithm. Low resolution patches carry the global information of the face and give a coarse but robust detection of the desired landmark. High resolution patches, using local details, refine this location. This process is combined with a bootstrap process and a statistical validation, both improving the system robustness. Combining independent point detection and prior knowledge on the point distribution, the proposed detector is robust to variable lighting conditions and facial expressions. This detector is tested on several databases and the results reported can be compared favorably with the current state of the art point detectors.