A Neuronal Planar Modeling for Handwriting Signature based on Automatic Segmentation

TL;DR

This paper introduces a novel planar neuronal model for offline handwriting signature verification, utilizing automatic segmentation into bands, and demonstrates promising results on both proprietary and public signature databases.

Contribution

It presents an innovative automatic segmentation approach and a planar neuronal model for signature verification, advancing the accuracy of offline signature analysis.

Findings

Effective segmentation into bands improves signature modeling.

Model tested on proprietary and public datasets shows promising results.

Achieved high verification accuracy on large signature databases.

Abstract

This paper deals with offline handwriting signature verification.We propose a planar neuronal model of signature image. Planarmodelsare generally based on delimiting homogenous zones ofimages; we propose in this paper an automatic segmentationapproach into bands of signature images. Signature image ismodeled by a planar neuronal model with horizontal secondarymodels and a verticalprincipal model. The proposed methodhas been tested on two databases. The first is the one we havecollected; it includes 6000 signaturescorresponding to 60writers. The second is the public GPDS-300 database including16200 signature corresponding to 300 persons. The achievedresults are promising.