On-line signature verification using a computational intelligence approach

For signature verification, there can be a large number of features available in a signature and not all these features are of use as some even could be unfavorable for verification of particular signatures. Also, the large number of features imposes difficulty in comparing instances. This may be worsened if observed peculiarities between features could not be drawn to benefit the comparison process. Hence, to determine a personalized subset of features and allowing for the inclusion of heuristics in verification are prime factors to consider in the design of the verification model. In this novel approach, genetic algorithm determines the optimal personalized features for each subject and fuzzy logic transforms the heuristics conceived by a human verifier to rules that govern the behavior of the automated verification system. Experimental results are presented to demonstrate the effectiveness of this scheme.