The methods of using ACOGA and geometric extrema characteristics for online signature verification

This paper presents a new method to select a segment-to-segment matching by analysing signature verification, accordingly curve segments used in signature verification and the regional feature contained in the curve segment are picked-up and the regional features are selected by ant colony optimization (ACO) algorithm and genetic algorithms (GAs). Namely, features selected are first encoded into chromosome, and descendible types are founded by ACOGA improved locally. The essential advantages of ACO including cooperativity, obustness, positive feedback and distributed nature were discuss and also the disadvantages of low convergence speed while the high adaptability of GAs were discussed too. Meanwhile, cross operation and mutation of genetic algorithms were introduced into the ACO. A new crossover method is also proposed to determine the number of curve segments. The experiment shows that the algorithms proposed can accurately find optimal features for signature verification and bring the lower FRR and FAR, thereby the veracity in online signature verification is enhanced.