The analysis of face images has been extensively applied for the recognition of individuals in several application domains. Most notably, faces not only convey information about the identity of the subject, but also a number of ancillary information, which may be equally useful to anonymously determine the characteristics of an individual. Even though the first applications of face recognition have been related to security and access control, nowadays the analysis of human faces is related to several applications including law enforcement, man-machine interaction, and robotics, just to mention a few. This chapter explores the analysis of face images.
TopIntroduction
Visual perception is probably the most important sensing ability for humans to enable social interactions and general communication. As a consequence, face recognition is a fundamental skill that humans acquire early in life and which remains an integral part of our perceptual and social abilities throughout our life span (Allison, Puce, & McCarthy, 2000;Bruce & Young, 1986). Not only faces provide information about the identity of people, but also about their membership in broad demographic categories of humans (including sex, race, and age), and about their current emotional state (Hornak, Rolls, & Wade, 1996;) (Tranel, Damasio, & Damasio, 1988; Calder, Young, Rowland, Perrett, Hodges, & Etcoff, 1996; Humphreys, Donnell, & Riddoch, 1993;Calder & Young, 2005). Humans “sense” these information effortlessly and apply it to the ever-changing demands of cognitive and social interactions.
This chapter aims to provide an overview of the most interesting applications of human face analysis and recognition. Due to space constraints this overview can not be exhaustive, yet it provides a good starting point for those who are willing to approach this challenging and fascinating technology and research field.
Human Face Analysis in “The Real World”
The difficulties often encountered in the analysis of human faces stems from the high variability of the face as an object. This is due to both intrinsic and extrinsic factors. The former include the plasticity of the face itself, the motion of the facial mussels producing different facial expressions, the feeding conditions changing the fat mass, the skin hydration, the presence of aesthetic products such as facial lotion and make-up, and the pose of the head. The latter include the illumination conditions, the background and the general environment, the imaging sensor and camera, the distance of the subject from the camera.
Security is possibly the application domain where face recognition systems have been most often deployed. Yet, these not always have been translated in a direct success.