A Frontal Face Detection Algorithm Using Fuzzy Classifier
Ramazan Taşaltı́n, Osman Taylan · Journal of King Abdulaziz University-Engineering Sciences · 2007
This paper describes a new approach for detecting faces whose size, position and pose are unknown in an image. Skin color and face border information are the primary key parameters to develop a fuzzy rule based classifier and to extract a face candidate from an image. At first, face candidate blobs were extracted using skin color information, then the blob was divided into four regions and the face borders are approximated by polynomials. Second, reference polynomials were extracted by examining different faces. As a result, the deviations from reference polynomials were used by a fuzzy classifier to decide whether the blob contains a face or not.