Antiforgery: a novel pseudo-outer product based fuzzy neural network driven signature verification system

Abstract

A novel pseudo-outer product based fuzzy neural network (POPFNN-TVR) driven signature verification system called the antiforgery system is presented in this paper. As Plamondon and Lorette have stated that the design of a signature verification system generally requires the solution of five types of problems: data acquisition, preprocessing, feature extraction, comparison process, and performance evaluation. However, unlike most existing automatic signature verification systems which employ traditional techniques (i.e. image processing techniques) to solve these problems, the proposed system is constructed on the basis of a novel fuzzy neural network called the POPFNN-TVR. The characteristics of POPFNN-TVR, such as the learning ability, generalization ability, and high computational ability, make antiforgery particularly powerful when verifying skilled forgeries. To demonstrate the efficacy of POPFNN-TVR and its application in the antiforgery system, several types of experiments have been designed and implemented in this work. The experimental results and analysis are presented at the end of the paper for discussion.