Paper Info
Title
Binary spectral minutiae representation with multi-sample fusion for fingerprint recognition.
Abstract
Biometric fusion is the approach to improve the biometric system performance by combining multiple sources of biometric information. The binary spectral minutiae representation is a method to represent a fingerprint minutiae set as a fixed-length binary string. This binary representation has the advantages of a fast operation and a small template storage. It also enables the combination of a biometric system with template protection schemes that require a fixed-length feature vector as input. In this paper, based on the spectral minutiae representation algorithm, we investigate the multi-sample fusion algorithms at the feature-, score-, and decision-level respectively. Furthermore, we propose different schemes to mask out unreliable bits. The algorithms are evaluated on the FVC2000-DB2 database and showed promising results.
Year
DOI
Venue
2010
10.1145/1854229.1854245
MM&Sec
Keywords
DocType
Citations 
spectral minutiae representation algorithm,fingerprint,binary spectral minutiae representation,fixed-length binary string,biometric system,multi-sample fusion algorithm,fixed-length feature vector,binary representation,biometric fusion,biometric system performance,template protection,biometrics,fingerprint recognition,biometric information,system performance,feature vector
Conference
1
PageRank 
References 
Authors
0.39
13
2
Name
Order
Citations
PageRank
Haiyun Xu113015.77
Raymond N. J. Veldhuis243954.16