An efficient method for the extraction of closed and open pores in fingerprint images

• Published in: 2019 16th International Multi-Conference on Systems, Signals & Devices (SSD) pp. 154 - 157
• Main Authors: Khmila, Houda, Smaoui, Nadia, Khanfir, Imen, Derbel, Houda
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.03.2019
• Subjects: Energy management; Feature extraction; fingerprint; Fingerprint recognition; high resolution; Image resolution; level 3; Morphological operators; pores extraction; Training
• ISSN: 2474-0446
• DOI: 10.1109/SSD.2019.8893238

Biometrics is a rising field in which technology improves our capacity to identify an individual. Protecting consumers against fraud or theft is one of the goals of biometrics. The benefit of biometric authentication is that each person has its own physical features which can't be modified, robbed or lost. The fingerprint is among the features that prove unique to an individual, especially, with the technological advancement of the sensors, the high-resolution fingerprint images are growing well known; the pores have been observed to be one of the brilliant nominees in enhancing the efficiency of automated fingerprint identification systems to keep up a high state of security. Our work is presented in this context. In fact, this paper proposes a new method based on morphologic operations aiming at extracting pores in high resolution fingerprint images. The proposed approach consists to extract the two types of pores (open and closed) by two different methods. We evaluate our approach on the PolyU-HRF database, and we compare the result to the existing methods in the literature.