Combining multiple matchers for fingerprint verification: A case study in biosecure network of excellence

We report on experiments for the fingerprint modality conducted during the First BioSecure Residential Workshop. Two reference systems for fingerprint verification have been tested together with two additional non-reference systems. These systems follow different approaches of fingerprint processing and are discussed in detail. Fusion experiments I volving different combinations of the available systems are presented. The experimental results show that the best recognition strategy involves both minutiae-based and correlation-based measurements. Regarding the fusion experiments, the best relative improvement is obtained when fusing systems that are based on heterogeneous strategies for feature extraction and/or matching. The best combinations of two/three/four systems always include the best individual systems whereas the best verification performance is obtained when combining all the available systems.RésuméVoici le rapport sur les expériences menées sur la modalité d’empreintes digitales pendant le premier atelier BioSecure Residential. Deux systèmes de référence pour la vérification d’empreinte digitale ont été examinés ainsi que deux systèmes additionnels sans référence. Ces systèmes suivent différentes approches pour le traitement des empreintes digitales, que nous allons présenter en de plus amples détails. En outre, nous présentons des expériences de fusion comportant différentes combinaisons de systèmes disponibles. Les résultats expérimentaux prouvent que la meilleure stratégie d’identification implique des mesures basées sur les minuties et la corrélation. Concernant les expériences de fusion, la meilleure amélioration relative est obtenue en fusionnant les systèmes basés sur des stratégies hétérogènes dans leur extraction de paramètres et/ou dans leur technique de comparaison. Les meilleures combinaisons de deux, trois, ou quatre systèmes incluent toujours le meilleur système. Le meilleur résultat en vérification est obtenu en combinant tous les systèmes disponibles.

[1]  Josef Bigün,et al.  Local Feature Extraction in Fingerprints by Complex Filtering , 2005, IWBRS.

[2]  Arun Ross,et al.  A hybrid fingerprint matcher , 2002, Object recognition supported by user interaction for service robots.

[3]  Stefan Fischer,et al.  Expert Conciliation for Multi Modal Person Authentication Systems by Bayesian Statistics , 1997, AVBPA.

[4]  Zsolt Miklós Kovács-Vajna,et al.  A Fingerprint Verification System Based on Triangular Matching and Dynamic Time Warping , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Anil K. Jain,et al.  Local Correlation-based Fingerprint Matching , 2004, ICVGIP.

[6]  J. Fierrez-Aguilar,et al.  On the effects of image quality degradation on minutiae- and ridge-based automatic fingerprint recognition , 2022, Proceedings 39th Annual 2005 International Carnahan Conference on Security Technology.

[7]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  J. González-Rodríguez,et al.  Image quality and position variability assessment in minutiae-based fingerprint verification , 2003 .

[9]  Javier Ortega-Garcia,et al.  An Improved Image Enhancement Scheme for Fingerprint Minutiae Extraction in Biometric Identification , 2001, AVBPA.

[10]  Gian Luca Marcialis,et al.  Fingerprint verification by fusion of optical and capacitive sensors , 2004, Pattern Recognit. Lett..

[11]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[12]  Juan J. Igarza,et al.  MCYT baseline corpus: a bimodal biometric database , 2003 .

[13]  Anil K. Jain,et al.  On-line fingerprint verification , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[14]  Javier Ortega-Garcia,et al.  From Biometrics Technology to Applications Regarding Face, Voice, Signature and Fingerprint Recognition Systems , 2002 .

[15]  G. Chollet,et al.  The 1st BioSecure Residential Workshop , 2005, ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005..

[16]  Arun Ross,et al.  Fingerprint Matching Using Feature Space Correlation , 2002, Biometric Authentication.

[17]  Loris Nanni,et al.  Combining Multiple Matchers for Fingerprint Verification: A Case Study in FVC2004 , 2005, ICIAP.

[18]  Arun Ross,et al.  A hybrid fingerprint matcher , 2003, Pattern Recognit..

[19]  Anil K. Jain,et al.  Handbook of Fingerprint Recognition , 2005, Springer Professional Computing.

[20]  Josef Bigün,et al.  Using Linear Symmetry Features as a Pre-processing Step for Fingerprint Images , 2001, AVBPA.