An improved 3-steps contactless fingerprint image enhancement approach for minutiae detection

Liu Xinwei (1) , Pedersen Marius (2) , Charrier Christophe (1) , Faouzi Alaya Cheikh (3) , Patrick Bours (3)

1 Equipe SAFE - Laboratoire GREYC - UMR6072
2 ColorLab - The Norvegian Research Color Laboratory
3 GUC - Gjøvik University College

Fingerprint enhancement is a critical step in fingerprint recognition systems. There are may existing contact-based fingerprint image enhancement methods, these methods have their own strengths and weaknesses. However, image enhancement approaches that can be used for contactless fingerprints are rarely considered and the number of such approaches is limited. Furthermore, the performance of existing contact-based fingerprint enhancement methods on the contactless fingerprint samples are unsatisfactory. Therefore, in this paper we propose an improved 3-step fingerprint image quality enhancement approach, which can be used for enhancing contactless fingerprint samples. The evaluation results show that, the proposed enhancement method improves the performance of fingerprint recognition system by reducing 7% and 15% EER, and increasing 30 and 40 detected minutiae compared to existing methods, respectively.

Mots clés: Contactless fingerprint; enhancement; minutiae; biometry

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Liu Xinwei, Pedersen Marius, Charrier Christophe, Faouzi Alaya Cheikh, Patrick Bours. An improved 3-steps contactless fingerprint image enhancement approach for minutiae detection. 6th European Workshop on Visual Information Processing (EUVIP), Oct 2016, Marsseille, France. ⟨hal-01375855⟩