Quantitative evaluation of face detection and tracking algorithms for head pose estimation in mobile platforms

Abstract

Face detection, face tracking and head pose estimation are commonly utilized in many computer vision applications related to face recognition, expression analysis, augmented reality and human computer interaction. Many different types of face detection and face tracking algorithms have been proposed by different research groups and based on the target platforms and applications, these algorithms have their own strengths and imitations. Yet a comprehensive intra and inter approach evaluation against a single data set is not available in the literature. In this paper, we present a comprehensive evaluation carried out on a set of selected face detection and tracking algorithms with respect to their accuracy, performance and robustness on both PC and mobile platforms.