Overview

Stan Z. Li

Microsoft Research Asia, Beijing 100080, China. ^[*]

Face detection is the first step in automated face recognition. Its reliability has a major influence on the performance and usability of the entire face recognition system. Given a single image or a video, an ideal face detector should be able to identify and locate all the present faces regardless of their position, scale, orientation, age, and expression. Furthermore, the detection should be irrespective of extraneous illumination conditions and the image and video content.

Face detection can be performed based on several cues: skin color (for faces in color images and videos), motion (for faces in videos), facial/head shape, facial appearance, or a combination of these parameters. Most successful face detection algorithms are appearance-based without using other cues. The processing is done as follows: An input image is scanned at all possible locations and scales by a subwindow. Face detection is posed as classifying the pattern in the subwindow as either face or nonface. The face/nonface classifier is learned from face and nonface training examples using statistical learning methods.

This chapter focuses on appearance-based and learning-based methods. More attention is paid to AdaBoost learning-based methods because so far they are the most successful ones in terms of detection accuracy and speed. The reader is also referred to review articles, such as those of Hjelmas and Low [12] and Yang et al. [52], for other face detection methods.