An efficient and reliable human resource management system based on a hybrid of face authentication and RFID technology

This paper focuses on the research and development of a human resource management (HRM) system which is based on face authentication and RFID technology for more efficient security and reliability. In the proposed system, a user ID is first read from the given RFID tag to retrieve the corresponding records from the database to be used in the authentication process together with the user image which is captured independently by a camera. Haar like features are exploited to allocate face candidates from the captured images and then classified by a SVM classifier into face and non-face samples, where the textureness and roughness of the samples are measured by multi-window BDIP and multi-window BVLC moments evaluated for window sizes of 2× 2, 3× 3 and 4× 4. The authentication process is then performed by utilization of well-known client specific Fisherface method, which is based on combination of PCA and LDA. The experiment showed that the system has achieved the authentication accuracy about 91.3 % with an increased reality and stability.