Parts-based face detection at multiple views

This paper presents a parts-based approach to face detection, that is intuitive, easy to implement and can be used in conjunction with other image understanding operations that use prominent facial features. Artificial neural networks are trained as view-specific parts detectors for the eyes, mouth and nose. Once these salient facial features are identified, results for each view are integrated through a Bayesian network in order to reach the final decision. System performance is comparable to other state-of the art face detection methods while providing support for different view angles and robustness to partial occlusions.