Studies of Fingerprint Template Selection and Update - Advances in Computational Science and Engineering - page 150

Studies of Fingerprint Template Selection and Update
Yong Li, Jianping Yin, En Zhu, Chunfeng Hu, and Hui Chen
School of Computer, National University of Defense Technology, Changsha, 410073, China
[e-mail], [e-mail], [e-mail],
[e-mail], [e-mail]
Abstract. A fingerprint recognition procedure usually contains two stages: reg-
istration and authentication. Most fingerprint recognition systems capture mul-
tiple samples of the same finger (e.g., eight impressions of a person's left index
finger) at the stage of registration. As a result, it is essential to select several
samples as templates. This paper proposes two algorithms maximum match
scores (MMS) and greedy maximum match scores (GMMS) based on match
scores for template selection. The proposed algorithms need not involve the
specific details about the biometric data. Therefore, they are more flexible and
can be used in various biometric systems. The two algorithms are compared
with Random and sMDIST on the database of FVC2006DB1A, and the experi-
mental results show that the proposed approaches can improve the accuracy of
biometric system efficiently. Based on the maximized score model, we propose
two strategies: ONLINE and OFFLINE for templates update and analyze the re-
lationship between the two strategies. Preliminary experiments demonstrate that
OFFLINE strategy gains better performance and GMMS performs better and
can gain steady improvement.
Keywords: biometric template, template selection, template update, match
score, fingerprint recognition.
1 Introduction
Biometric recognition refers to the use of distinctive physiological or behavioral char-
acteristics for automatically confirming the identity of a person. It is becoming appar-
ent that unibiometric system is not sufficient to meet the requirement of system which
need very high performance and security. Multibiometrics which combines more
information is expected to alleviate the limitations of unibiometric systems [1]. Fin-
gerprint recognition is the most popular and reliable biometric technique for auto-
matic personal identification and plays an important role in multibiometric system
from application to research activities. Biometric systems usually include two stages:
registration and authentication. In practice, most biometric systems will capture mul-
tiple samples of the same biometric trait at the stage of registration. For example,
some fingerprint systems require the user to enroll eight impressions into the system.
There are three techniques to deal with the multiple samples literally. The first
method [3,4,11] is template selection which chooses several samples as templates