Abstract

An algorithm for locating quasi-frontal views of human faces in cluttered scenes is presented. The algorithm works by coupling a set of local feature detectors with a statistical model of the mutual distances between facial features; it is invariant with respect to translation, rotation (in the plane), and scale and can handle partial occlusions of the face. On a challenging database with complicated and varied backgrounds, the algorithm achieved a correct localization rate of 95% in images where the face appeared quasi-frontally. 1 Introduction The problem of face recognition has received considerable attention from the computer vision community, and a number of techniques have been proposed in the literature [3, 11, 12, 13, 14, 16, 17, 19]. However, in most of these studies the face was in a benign environment from which it could easily be extracted, or it was assumed to have been pre-segmented. For any of these recognition algorithms to work in a general setting, we need a system...

Citations