Automatic Image-based Face Analysis Systems Overview

Face analysis systems have recently gained popularity due to the large number of potential applications across a wide range of industries. Various types of information can be extracted from an image of a face including: face location and size, location of characteristic facial landmark points, 3D head pose, facial expression and emotion, gaze direc­ tion and biometric information (i.e. age, gender and race). Most of these problems are solved using machine learning techniques based on large sets of training samples. Fur­ thermore, information from these different tasks is often complementary and can be used to enhance the accuracy of the algorithms. A systematic overview of current ap­ proaches to face analysis tasks is presented as an intro­ duction to this growing research field.