Face recognition robust to head pose from one sample image

Most face recognition systems only work well under quite constrained environments. In particular, the illumination conditions, facial expressions and head pose must be tightly controlled for good recognition performance. In 2004, we proposed a new face recognition algorithm, Adaptive Principal Component Analysis (APCA) [4], which performs well against both lighting variation and expression change. But like other eigenface-derived face recognition algorithms, APCA only performs well with frontal face images. The work presented in this paper is an extension of our previous work to also accommodate variations in head pose. Following the approach of Cootes et al, we develop a face model and a rotation model which can be used to interpret facial features and synthesize realistic frontal face images when given a single novel face image. We use a Viola-Jones based face detector to detect the face in real-time and thus solve the initialization problem for our Active Appearance Model search. Experiments show that our approach can achieve good recognition rates on face images across a wide range of head poses. Indeed recognition rates are improved by up to a factor of 5 compared to standard PCA.

Refinement-robust fairness

We motivate and study the robustness of fairness notions under refinement of transitions and places in Petri nets. We show that the classical notions of weak and strong fairness are not robust and we propose a hierarchy of increasingly strong, refinement-robust fairness notions. That hierarchy is based on the conflict structure of transitions, which characterizes the interplay between choice and synchronization in a fairness notion. Our fairness notions are defined on non-sequential runs, but we show that the most important notions can be easily expressed on sequential runs as well. The hierarchy is further motivated by a brief discussion on the computational power of the fairness notions.