etection Using Local Maxima

Automatic human face detection in dagital images with a complex environment i s still an unsolved problem in computer vision and pattern recognition. It has several uses like human face recognition, content based image retrieval and model based video coding. In this paper we present an automatzc human face detection system in with which several methods are tested and compared. The underlying principle of the system is to compare subimages of the image p yramid, spanned by the input image, with a set of ’nose-eye’ templates. However this comparison is not done on the entire set of subimages of the image p yramid, but on a small subset, which is defined by the ’Local Maxima Method’. False positives are found by using a set of non-face templates. The system is tested on two databases, which each include over 1000 images.