A Memory-Efficient Fingerprint Verification Algorithm Using a Multi-Resolution Accumulator Array

Etri Journal (Impact Factor: 0.74). 01/2003; 25(3):179-186. DOI: 10.4218/etrij.03.0102.3316

ABSTRACT Using biometrics to verify a person's identity has several advantages over the present practices of personal identification numbers (PINs) and passwords. At the same time, improvements in VLSI technology have recently led to the introduction of smart cards with 32-bit RISC processors. To gain maximum security in verification systems using biometrics, verification as well as storage of the biometric pattern must be done in the smart card. However, because of the limited resources (processing power and memory space) of the smart card, integrating biometrics into it is still an open challenge. In this paper, we propose a fingerprint verification algorithm using a multi-resolution accumulator array that can be executed in restricted environments such as the smart card. We first evaluate both the number of instructions executed and the memory requirement for each step of a typical fingerprint verification algorithm. We then develop a memory-efficient algorithm for the most memory-consuming step (alignment) using a multi- resolution accumulator array. Our experimental results show that the proposed algorithm can reduce the required memory space by a factor of 40 and can be executed in real time in resource-constrained environments without significantly degrading accuracy.

  • Ieice Electronic Express. 01/2008; 5(4):136-144.
  • [Show abstract] [Hide abstract]
    ABSTRACT: Fingerprint verification in biometric technologies is the most widely-used user identification method because of its confidence and convenience. The minutiae-based method has been frequently used, but it has limitations in performance. These days, there have been many studies on enhancement of performance using other information rather than minutiae. The image-based method uses contrast of images to verify fingerprints. This study analyzed changes in performance according to size and form of images to be compared to identify the performance of the verification using binary fingerprint images. The results showed that the performance was good when the center of fingerprints was included while Zero False Match Rate (ZeroFMR) decreased when the size of compared area was below 64 �? 64. And when the compared area was the center of the fingerprint image, verification and security performance were enhanced. In particular, if information on ridge in the center of the image was used, ZeroFMR could be evaluated though the ridge and valley were not used together.
    The Second International Conference on Future Generation Communication and Networking, FGCN 2008, Volume 2, Workshops, Hainan Island, China, December 13-15, 2008; 01/2008
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: There are at least two principal approaches to prevent users from sharing their anonymous credentials: adding valuable secrets into the system the user does not want to share or embedding biometric access control. This paper seeks to identify possible fields of application and to compare both approaches with respect to the credentials’ non-transferability. The paper shows that both approaches do not ensure the non- transferability of anonymous credentials, but may be applicable in some fields. On the one hand, it might be hard to find valuable secrets to really prevent the sharing of credentials, in particular with close family members. On the other hand, biometric sensors embedded in a smartcard can be circumvented with some effort, especially if access control is unattended. Although the combination of both approaches may prevent more users from sharing their credentials, it suffers from restrictions of both approaches and from the effort needed to put it in place. However, assuming that anonymous credentials will probably not be used in high-security environments, both approaches might be sufficient to prevent sharing in some applications. If the users already possess personal digital assistants, embedded valuable secrets are a quite cheap solution, even though they raise the system’s value. If access control is attended, biometric sensors are reasonably safe and limit the possibility of unintentionally sharing the credentials for free.
    07/2009: pages 107-118;


Available from