Deep rule-based classifier for finger knuckle pattern recognition system
- PDF / 4,486,894 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 40 Downloads / 230 Views
ORIGINAL PAPER
Deep rule‑based classifier for finger knuckle pattern recognition system Abdelouahab Attia1,3 · Zahid Akhtar2 · Nour Elhouda Chalabi3 · Sofiane Maza1 · Youssef Chahir4 Received: 21 March 2020 / Accepted: 8 October 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract In this paper, we proposed a novel finger knuckle pattern (FKP) based personal authentication system using multilayer deep rule based (DRB) classifier. The presented approach is completely data-driven and fully automatic. However, the DRB classifier is generic and can be used in variety of classification or prediction problems. In particular, from the input finger knuckle, two kinds of features (i.e., Binarized Statistical Image Features and Gabor Filer bank) are extracted, which are then fed to fuzzy rules based DRB classifier to determine whether the user is genuine or impostor. Experimental results in the form of accuracy, error equal rate (EER) and receiver operating characteristic (ROC) curves demonstrate that presented DRB classifier is a powerful tool in FKP based biometric identification system. Experiments are reported using publicly available FKP PolyU database provided by University of Hong Kong. Experiments using this database show that the presented framework, in this study, can attain performance better than previously proposed methods. Moreover, score level fusion of all FKP modalities with BSIF + DRB yielded an equal error rate of 0.19% and an accuracy of 99.65%. Keywords Deep rule based classifier · BSIF · Gabor filter bank · Finger knuckle pattern
1 Introduction In today’s highly interconnected society, automated personal identification methods have become crucial for security and privacy (Angelov and Gu 2018; Bao et al. 2018; Angelov and Sperduti 2016). One of person recognition methods is biometrics, which is considered as an alternative security system to traditional authentication and identification methods such as ID card, passwords, code PIN. Biometrics facilitate the process of recognizing a person based on their physiological, behavioral or chemical characteristics * Abdelouahab Attia [email protected] 1
LMSE Laboratory, Mohamed El Bachir El Ibrahimi University of Bordj Bou Arreridj, 34000 Bordj Bou Arreridj, Algeria
2
State University of New York Polytechnic Institute, Albany, NY, USA
3
Computer Science Department, Mohamed El Bachir El Ibrahimi University of Bordj Bou Arreridj, 34000 Bordj Bou Arreridj, Algeria
4
Image Team GREYC-CNRS UMR, University of Caen, Caen, France
(Adeoye 2010). Numerous biometric traits have been used in diverse applications ranging from border crossing to mobile authentication (Zhang et al. 2018; Akhtar et al. 2011a, b). In fact, many different biometric traits have been investigated widely such as fingerprint, iris, ear, finger knuckle print, palm print, face etc. (Chaa et al. 2017; Jaswal et al. 2017a). Recently, finger knuckle print (FKP) (Cappelli et al. 2010), which is included in the hand based biometric traits, have been
Data Loading...
