Abstract
We propose the use of Morphological Multiscale Fingerprints (MMF) for Face Localization. The MMF s computed as the local maxima and minima preserved up to a certain scale in a multiscale analysis based on morphological erosion and dilation. This approach belongs to the class of global image feature extraction approaches that can be combined with others to ensure robust face localization. No structural relationships between face elements are taken into account. We compare this approach to the eigenface approach to face detection with clear superior results.