Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Filterbank-based fingerprint matching
IEEE Transactions on Image Processing
Robust extraction of secret bits from minutiae
ICB'07 Proceedings of the 2007 international conference on Advances in Biometrics
Hi-index | 0.00 |
This paper provides a solution to converting a varied-length and unordered fingerprint minutiae set into a fixed-length and ordered vector. The proposed method transforms the minutiae in form of discrete coordinates into a fixed-size gray-level raster image by linear combination of pixels looked up against a randomly created 2-dimensional texture image. Then it becomes a trivial task to extract a fixed-length feature vector with ordered components from the fixed-size raster image. Experiments on the public fingerprint database FVC2002DB2_A demonstrate the effectiveness of the proposed method. Via a keyed generation of the random raster texture image, the proposed method enhances the privacy of a fingerprint minutiae template against information leakage. The same idea applies to any other cases requiring a transformation of discrete points based features to fixed-length and ordered features, e.g., media fingerprinting/hashing applications.