Paper Info
Title
Asra: Automatic Singular Value Decomposition-Based Robust Fingerprint Image Alignment
Abstract
Fingerprint-based user identification and authentication are now used in many applications, but achieving absolute accuracy (eliminating false matches) still remains an issue. One of the reasons behind this issue is inappropriate image alignment prior to the feature extraction. In this paper, a robust Singular Value Decomposition (SVD) based fingerprint alignment method is proposed which automatically aligns the segmented and rotated image within the angular range - 90(0) to 90(0). Further, it overcomes the limitations of the existing fingerprint alignment methods as it neither depends on the quality of the image nor requires any reference image. The effectiveness of the approach has been tested with the standard fingerprint image databases FVC2002 (DB1, DB2, DB3, and DB4), FVC2004 (DB1, DB2, DB3, and DB4) and captured sensor images in an uncontrolled environment. The proposed approach was found to be efficient both in terms of accuracy and computational time. Also, it worked well for both database images and captured sensor images.
Year
DOI
Venue
2021
10.1007/s11042-021-10560-5
MULTIMEDIA TOOLS AND APPLICATIONS
Keywords
DocType
Volume
Singular value decomposition, Segmentation, Fingerprint alignment, Uncontrolled environment
Journal
80
Issue
ISSN
Citations 
10
1380-7501
0
PageRank 
References 
Authors
0.34
0
4
Name
Order
Citations
PageRank
Fagul Pandey100.34
Priyabrata Dash200.34
Debasis Samanta322737.98
Monalisa Sarma4105.24