Document scanners for minutiae-based palmprint recognition: a feasibility study
- PDF / 2,424,661 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 64 Downloads / 191 Views
ORIGINAL ARTICLE
Document scanners for minutiae‑based palmprint recognition: a feasibility study Manuel Aguado‑Martínez1,2 · José Hernández‑Palancar1,2 · Katy Castillo‑Rosado1,2 · Rodobaldo Cupull‑Gómez1,2 · Christof Kauba1,2 · Simon Kirchgasser1,2 · Andreas Uhl1,2 Received: 7 February 2020 / Accepted: 14 October 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Highly expensive capturing devices and barely existent high-resolution palmprint datasets have slowed the development of forensic palmprint biometric systems in comparison with civilian systems. These issues are addressed in this work. The feasibility of using document scanners as a cheaper option to acquire palmprints for minutiae-based matching systems is explored. A new high-resolution palmprint dataset was established using an industry-standard Green Bit MC517 scanner and an HP Scanjet G4010 document scanner. Furthermore, a new enhancement algorithm to attenuate the negative effect of creases in the process of minutiae extraction is proposed. Experimental results highlight the potentialities of document scanners for forensic applications. Advantages and disadvantages of both technologies are discussed in this context as well. Keywords High resolution-palmprint matching · Palmprint recognition · Minutiae-based recognition · Document scanner
1 Introduction Palmprint applications have proven to be highly reliable for a wide range of scenarios. As a stand-alone trait, or in combination with others, palmprint biometrics have been extensively studied by the scientific community [8, 9, 11, 35, 36]. Palms have a huge area containing rich and distinctive * Manuel Aguado‑Martínez [email protected] José Hernández‑Palancar [email protected] Katy Castillo‑Rosado [email protected] Rodobaldo Cupull‑Gómez [email protected] Christof Kauba [email protected] Simon Kirchgasser [email protected] Andreas Uhl [email protected] 1
Advanced Technologies Application Center, 7ma A #21406 e/214 y 216, Siboney, Playa, C.P. 12200 Havana, Cuba
Department of Computer Sciences, University of Salzburg, Salzburg, Austria
2
features making them highly individual. Furthermore, the urgent need for palmprint forensic applications in law enforcement was introduced to the scientific community by [16], where several studies were cited regarding the number of latent palmprints found at crime scenes. Nevertheless, advances in forensic palmprint biometric systems have been slower compared to those on civilian systems until today. Principal lines and texture information can be extracted from low-resolution images and are distinctive enough for civilian applications. Forensic applications require more fine-grained features like minutiae. For this, high-resolution images (500 ppi) are needed [22]. Bigger and more expensive devices (3000–4000 USD) are required to capture palmprint images at such resolution. Added to this, the scarce existence of high-resolution palmprint datasets has prevented more extensive research in this area. Moreover, i
Data Loading...
