A significant step in automatic fingerprint matching is to automatically and constantly extract minutiae from the input fingerprint images. However, the presentation of a minutiae extraction algorithm relies heavily on the excellence of the input fingerprint images. In order to make certain that the presentation of an automatic fingerprint identification/verification system will be strong with respect to the excellence of input fingerprint images, it is necessary to incorporate a fingerprint enhancement algorithm in the minutiae extraction module. We present a highspeed fingerprint authentication algorithm, which can adaptively improve the simplicity of ridge and valley structures of input fingerprint images based on the estimated local ridge orientation and frequency. We have evaluated the presentation of the image enhancement algorithm using the goodness index of the extracted minutiae and the exactness of an online fingerprint verification system. An experimental result shows that the verification algorithm improves both the goodness appearance and the verification accuracy.
[1]
M. S. Kumbhar,et al.
An Identity-Authentication System Using Fingerprints
,
2012
.
[2]
Y. Al-Najjar,et al.
Minutiae extraction for fingerprint recognition
,
2008,
2008 5th International Multi-Conference on Systems, Signals and Devices.
[3]
Sharath Pankanti,et al.
Fingerprint enhancement
,
1996,
Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96.
[4]
Chen Gang,et al.
An improved OPTA fingerprint thinning algorithm based on neighborhood searching
,
2012,
2012 International Conference on Computer Science and Information Processing (CSIP).
[5]
Fanglin Chen,et al.
Hierarchical Minutiae Matching for Fingerprint and Palmprint Identification
,
2013,
IEEE Transactions on Image Processing.
[6]
S. K. Mitra,et al.
A rough-set based binarization technique for fingerprint images
,
2012,
2012 IEEE International Conference on Signal Processing, Computing and Control.