Palmprint Image Quality Measurement Algorithm

Biometric systems proposed in the literature have reached a correct performance level when the acquired samples are of good quality. However, the performances fall when these samples are of poor quality. In order to face up to this problem, integration of modules for measuring sample quality in the process of biometric recognition is necessary. In this paper, we propose a new approach for measuring palmprint image quality in terms of illumination, and integrate it in the biometric system to reject the palmprint of poor illumination and to make new session of acquisition. The proposed approach has been evaluated on PolyU Palmprint database. The achieved results are very encouraging.