Abstract
Recent years have witnessed lots of development on face recognition systems including the ability to adapt to new genuine user features. Self-adapted Face Recognition systems are powerful tools to overcome the limitation of performance degradation over time. In this paper, a self-adapted face verification system (AFVS) that can efficiently classify genuine user samples for the update process using deep learning techniques has been proposed. The adaptivity feature of the proposed system model ensures performance stability in the long run. The proposed model has been developed using deep learning techniques which showed improved performance on Krassar model with higher F1-score and more tolerance to facial changes than the state-of-the-art face verification models.