Forensic Signature Verification Competition 4NSigComp2010 - Detection of Simulated and Disguised Signatures

Abstract

This competition scenario aims at a performance comparison of several automated systems for the task of signature verification. The systems have to rate the probability of authorship and non-authorship of signatures. In particular they have to determine whether questioned signatures are simulated disguised or the normal signature of the reference writer. Furthermore, the results will be compared to forensic handwriting examiners (FHEs) opinions on the same tasks. As such, to the best of the authors' knowledge, this scenario will be the first attempt in literature to relate system performances to the performance of FHEs who gave their opinion on exactly the the same signatures.

Enhanced on-line signature verification based on skilled forgery detection using Sigma-LogNormal Features

“…In order to encourage further research efforts in the detection of skilled forgeries, several international signature verification competitions have recently included tasks on this topic, from 4NSigComp2010 [11] to SigWiComp2013 [13]. The comparison of the automatic results to forensic handwriting examiners opinions showed that those results were not far away from human expert decisions.…”

ICFHR 2012 Competition on Automatic Forensic Signature Verification (4NsigComp 2012)

“…From these 100 questioned signatures, 3 are genuine, 90 simulated/forged, and 7 disguised signatures. For further details refer to [8].…”

“…These signatures are more difficult to analyze compared to the signatures produced in controlled environments. In order to investigate these signatures and evaluate the performance of some of the stateof-the-art systems on data containing disguised signatures, we previously organized the 4NsigComp2010 [8]. It was the first signature verification competition focusing explicitly the classification of disguised, simulated/forged and genuine signatures.…”

“…• First International Signature Verification Competition (SVC 2004), online data, 100 signature sets: 20 (genuine, forged)/author [5] • BioSecure Signature Evaluation Campaign 2009, online data from DS2-382, DS3-382 [6] • SigComp 2009 [7], online and offline data, 1 reference signature (several authors) • 4NSigComp 2010 [8], offline data, 25 reference signatures (1 author) • SigComp 2011 [9], online and offline data Chinese and Dutch signatures, 12 reference signatures (several authors)…”

Towards a Shared Conceptualization for Automatic Signature Verification

“…5 It involves various genres of natural and unnatural handwriting. Due to space limitations, we will focus only on the main categories of signature types that are relevant to the discussion at hand.…”