An Attentive Processing Strategy for the Analysis of Facial Features

Facial landmarks such as eye corners, mouth corners or nose edges are important features for many applications in face recognition. The exact detection of these landmarks, however, is not an easy task because of the high individual variability of facial images and therefore, of the tremendous complexity of all the low-level features existing within the image. For instance, a precise and reliable detection of the eye corners has not been successfully solved until now. However, the knowledge of the exact position of these landmarks in the facial image is important for many matching and face processing tasks. For the classification and discrimination of dysmorphic facial signs a precise and reliable detection of a certain set of anatomical facial landmarks is particularly necessary. For this, an attentive processing strategy has been developed which puts the focus of the processing on only those salient image areas which are really needed to solve the several subtasks. The fundamental idea of the approach presented is to concentrate the artificial attention upon only a small fraction of the existing low-level features within a spatially well restricted image area.