A Novel Approach to Access Control Based on Face Recognition

In this paper, we introduce an approach to access control based on detecting and recognizing faces with novel methods. The goal is to build an automatic face recognition system which authorizes the access to the laboratory room for only certain persons while denying the access for the others. For this purpose, a camera is set in the door looking at the corridor and the captured frames are analyzed. The analysis starts by selecting the regions of interest in the images using either texture-based background subtraction or skin locus based color segmentation. Once the regions of interest are defined, a fast face detection scheme is launched. Then, the extracted faces are compared to those in the predefined database to determine whether the individuals are allowed to enter the room or not. Among the novelties of our approach is the use of the Local Binary Pattern (LBP) texture features for face recognition and background subtraction.