Component-Based Approach to Face Detection

Motivation: Faces form a class of visually similar objects that simplifies the generally difficult task of object detection. However, the problem of pose invariance is still unsolved. There are three basic ideas behind partor component-based detection of objects. First, some objects classes can be described well by a few characteristic object parts and their geometrical relation. Second, the patterns of some object parts can might less under pose changes than the pattern belonging to the whole object. Third, a component-based approach might be more robust against partial occlusions than a global approach. Fourth, recent psycho-physiological experiments show that building a hierarchy of simple detector would be close to the way the brain works.