A Scheme for Face Recognition in Complex Environments

Abstract

In this paper, the authors propose a scheme for human face recognition in complex environments. The proposed scheme consists of three phases: moving object removal, face detection and face recognition. It could be applied to certain specific environments such as computer users in office, shopping mall, and reception or pokie machine gamblers in casinos. In these environments, the target human face for recognizing will be considered as the foreground and the moving objects (such as cars, walking persons etc) as the background. The objective of this paper is to implement a scheme for human face recognition so as to improve recognition precision and reduce false alarms. The scheme can be applied to prevent computer users or gamblers from sitting too long in front of the screens in offices or pokie machines in casinos. To the best of the authors' knowledge, this is the first time face recognition in complex environments has been taken into consideration.