Computer Vision, Graphics, and Image Processing
On-Line Fingerprint Verification
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Multichannel Approach to Fingerprint Classification
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fingerprint Classification by Directional Image Partitioning
IEEE Transactions on Pattern Analysis and Machine Intelligence
FVC2000: Fingerprint Verification Competition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Visualizing Nonlinear Vector Field Topology
IEEE Transactions on Visualization and Computer Graphics
Vector Field Analysis for Oriented Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence
Systematic Methods for the Computation of the Directional Fields and Singular Points of Fingerprints
IEEE Transactions on Pattern Analysis and Machine Intelligence
Complex Filters Applied to Fingerprint Images Detecting Prominent Symmetry Points Used for Alignment
ECCV '02 Proceedings of the International ECCV 2002 Workshop Copenhagen on Biometric Authentication
Handbook of Fingerprint Recognition
Handbook of Fingerprint Recognition
IEEE Transactions on Image Processing
A model-based method for the computation of fingerprints' orientation field
IEEE Transactions on Image Processing
A Pruning Approach Improving Face Identification Systems
AVSS '09 Proceedings of the 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance
A novel technique for singular point detection based on Poincaré index
Proceedings of the 9th International Conference on Advances in Mobile Computing and Multimedia
| Hi-index | 0.00 |
As an important feature of fingerprints, singular points (includingcores and deltas) not only represent the local ridge pattern characteristics, but also determine the topological structure (i.e. fingerprint type). In this paper, we have performed analysis for singular points in two aspects. (1) Based on the topology theory in 2D manifold, we deduced the relationship between cores and deltas in fingerprints. Specifically we proved that every completely captured fingerprint should have the same number of cores and deltas. We also proposed a flexible method to compute the Poincare Index for singular points. (2) We proposed a novel algorithm for singular point detection using global orientation field. After the initial detection with the widely-used Poincare Index method, the optimal singular points are selected to minimize the difference between the original orientation field and the model-based orientation field reconstructed from the singular points. The core-delta relation is used as a global constraint for final decision. Experimental results showed that our algorithm is rather accurate and robust.