Selecting optimal classification features for SVM based elimination of incorrectly matched minutiae

Abstract

Rather than use arbitrary matching threshold values and a heuristic set of features while comparing minutiae points during the fingerprint verification process, we develop a system which considers only the optimal features, which contain the highest discriminative power, from a predefined feature set. For this, we use a feature selection algorithm which adds features, one at a time, till it arrives at an optimal feature set of the target size. The classifier is trained on this feature set, on a two class problem representing pairs of matched minutiae points belonging to fingerprints of same and different users. During the test phase, the system generates a number of candidate matched minutiae pairs; features from each of them are extracted and given to the classifier. Those that are incorrectly matched are eliminated from the scoring algorithm. We have developed a set of seven candidate features, and tested our system using the FVC 2002 DB1 fingerprint database. We study how feature sets of different sizes affect the accuracy of the system, and observe how additional features not necessarily would improve the performance of a classifier. This is illustrated in how using a 3 feature set gives us the most accurate system and using bigger feature sets cause a slight drop in accuracy.

Computational Intelligence for Biometric Applications: a Survey

“…The most popular matching methods are based on minutiae representations, where the matching has to pair the different minutiae points. In this context, many works have applied learning-based techniques such as SVMs [52], while fuzzy systems have been used to cope with nonlinear distortions [53]. In addition, CI approaches that do not rely on minutiae, but on the full image, are providing promising results [79].…”