EE Seminar: Robust features for facial action recognition
Speaker: Nadav Israel,
M.Sc. student under the supervision of Prof. Lior Wolf and Shai Avidan
Monday, Febuary 13th, 2017 at 15:30
Room 011, Kitot Hashmal., Faculty of Engineering
Robust features for facial action recognition
Abstract
Automatic recognition of facial gestures is becoming increasingly important as real world AI agents become a reality.
In the last years, a growing number of applications appeared, which require detailed information about human faces from video data streams. Examples are interactive mobile service robots or other man-machine-systems, whose dialog are to be adapted to the current emotional state of the interaction partner. For that purpose, amongst other describing features, the interpretation of the facial expression of the user is necessary.
In this paper, we present an automated system that recognizes facial gestures by capturing local changes and encoding the motion into a histogram of frequencies.
We evaluate the proposed method by demonstrating its effectiveness on spontaneous face action benchmarks: the FEEDTUM dataset, the Pain dataset and the HMDB51 dataset. The results show that, compared to known methods, the new encoding methods significantly improve the recognition accuracy and the robustness of analysis for a variety of applications.
