Facial analysis applying an attentive processing strategy
Rainer Herpers, Gerald Sommer · 2002
A technical realization of an attentional mechanism localizing and analyzing prominent facial regions in gray-level images is presented. By adopting the gaze control principles of the HVS for developing an image processing system, a complex image analysis problem may be decomposed into a number of subproblems which can be solved step by step in a simpler way. The attentive processing strategy starts with the localization of the prominent facial regions based on a saliency representation carrying all the information needed to select and restrict the extent of the prominent facial regions. Subsequently, the detected and now spatially limited regions are classified to evaluate the benefit of applying more detailed analysis methods. During the detailed analysis step the exact positions of anatomical landmarks or keypoints such as eye and mouth centers are determined. Fundamental to the attentive processing strategy is that all processing modules consider and process only prominent and really characteristic image structures. Only those images structures are considered which contribute to the solution of the actual processing task. The attentive processing strategy proposed is able to cope with variations due to the perspective angle or pose, orientation, illumination, and contrast of the studied facial images.