Abstract Effective student attendance management in higher educational institutions represents a big challenge for faculty members that need fast and accurate approaches. The traditional attendance manual approach is prone to spoofing and wasting a lot of faculty/students time and poor accuracy especially in the case of large student numbers. This paper presents an effective solution for the real-time student attendance management problem in large lecture halls. Fast response time and high accuracy imply using high-speed technologies and processes for student identification. In this paper, Radio Frequency Identification (RFID) and novel face recognition and identification approaches have been proposed and evaluated. A multimodal approach for student identification combined the power of both the traditional RFID approach and Multi-Scale Structural Similarity (MS-SSIM) index. Capturing the authentic face variability from a sequence of video frames has been considered for the recognition of faces and resulted in system robustness against the variability of facial features. Experimental results indicated an improvement in the performance of the proposed system compared to the state-of-the-art approaches at a rate between 2% and 5%. In addition, it decreased the time three times if compared with the state-of-the-art techniques, such as Extreme Learning Machine (ELM). Finally, it achieved an accuracy of 99%.