User Dependent Features in Online Signature Verification

TL;DR

This paper introduces a user-dependent feature selection method for online signature verification, utilizing symbolic representation and clustering to improve accuracy by tailoring features to individual users.

Contribution

It presents a novel user-dependent feature selection and symbolic clustering approach for online signature verification, differing from traditional methods that use uniform features for all users.

Findings

Effective in distinguishing genuine signatures from forgeries

Improves verification accuracy over traditional methods

Validated on MCYT datasets with promising results

Abstract

In this paper, we propose a novel approach for verification of on-line signatures based on user dependent feature selection and symbolic representation. Unlike other signature verification methods, which work with same features for all users, the proposed approach introduces the concept of user dependent features. It exploits the typicality of each and every user to select different features for different users. Initially all possible features are extracted for all users and a method of feature selection is employed for selecting user dependent features. The selected features are clustered using Fuzzy C means algorithm. In order to preserve the intra-class variation within each user, we recommend to represent each cluster in the form of an interval valued symbolic feature vector. A method of signature verification based on the proposed cluster based symbolic representation is also presented. Extensive experimentations are conducted on MCYT-100 User (DB1) and MCYT-330 User (DB2) online signature data sets to demonstrate the effectiveness of the proposed novel approach.