Writer-independent handwritten signature verification

Swanepoel, Jacques Philip (2015-12)

Thesis (PhD)--Stellenbosch University, 2015

Thesis

AFRIKAANSE OPSOMMING : In hierdie verhandeling stel ons 'n nuwe strategie vir outomatiese handtekening-verifikasie voor. Die voorgestelde raamwerk gebruik 'n skrywer-onafhanklike benadering tot handtekening- modellering en is dus in staat om bevraagtekende handtekeninge, wat aan enige skrywer behoort, te bekragtig, op voorwaarde dat minstens een outentieke voorbeeld vir vergelykingsdoeleindes beskikbaar is. Ons ondersoek die tradisionele statiese geval (waarin 'n bestaande pen-op-papier handtekening vanuit 'n versyferde dokument onttrek word), asook die toenemend gewilde dinamiese geval (waarin handtekeningdata outomaties tydens ondertekening m.b.v. gespesialiseerde elektroniese hardeware bekom word). Die statiese kenmerk-onttrekkingstegniek behels die berekening van verskeie diskrete Radontransform (DRT) projeksies, terwyl dinamiese handtekeninge deur verskeie ruimtelike en temporele funksie-kenmerke in die kenmerkruimte voorgestel word. Ten einde skryweronafhanklike handtekening-ontleding te bewerkstellig, word hierdie kenmerkstelle na 'n verskil-gebaseerde voorstelling d.m.v. 'n geskikte digotomie-transformasie omgeskakel. Die klassikasietegnieke, wat vir handtekeking-modellering en -verifikasie gebruik word, sluit kwadratiese diskriminant-analise (KDA) en steunvektormasjiene (SVMe) in. Die hoofbydraes van hierdie studie sluit twee nuwe tegnieke, wat op die bou van 'n robuuste skrywer-onafhanklike handtekeningmodel gerig is, in. Die eerste, 'n dinamiese tydsverbuiging digotomie-transformasie vir statiese handtekening-voorstelling, is in staat om vir redelike intra-klas variasie te kompenseer, deur die DRT-projeksies voor vergelyking nie-lineêr te belyn. Die tweede, 'n skrywer-spesieke verskil-normaliseringstrategie, is in staat om inter-klas skeibaarheid in die verskilruimte te verbeter deur slegs streng relevante statistieke tydens die normalisering van verskil-vektore te beskou. Die normaliseringstrategie is generies van aard in die sin dat dit ewe veel van toepassing op beide statiese en dinamiese handtekening-modelkonstruksie is. Die stelsels wat in hierdie studie ontwikkel is, is spesi ek op die opsporing van hoë-kwaliteit vervalsings gerig. Stelselvaardigheid-afskatting word met behulp van 'n omvattende eksperimentele protokol bewerkstellig. Verskeie groot handtekening-datastelle is oorweeg. In beide die statiese en dinamiese gevalle vaar die voorgestelde SVM-gebaseerde stelsel beter as die voorgestelde KDA-gebaseerde stelsel. Ons toon ook aan dat die stelsels wat in hierdie studie ontwikkel is, die meeste bestaande stelsels wat op dieselfde datastelle ge evalueer is, oortref. Dit is selfs meer belangrik om daarop te let dat, wanneer hierdie stelsels met bestaande tegnieke in die literatuur vergelyk word, ons aantoon dat die gebruik van die nuwe tegnieke, soos in hierdie studie voorgestel, konsekwent tot 'n statisties beduidende verbetering in stelselvaardigheid lei.

ENGLISH ABSTRACT : In this dissertation we present a novel strategy for automatic handwritten signature verification. The proposed framework employs a writer-independent approach to signature modelling and is therefore capable of authenticating questioned signatures claimed to belong to any writer, provided that at least one authentic sample of said writer's signature is available for comparison. We investigate both the traditional off-line scenario (where an existing pen-on-paper signature is extracted from a digitised document) as well as the increasingly popular on-line scenario (where the signature data are automatically recorded during the signing event by means of specialised electronic hardware). The utilised off-line feature extraction technique involves the calculation of several discrete Radon transform (DRT) based projections, whilst on-line signatures are represented in feature space by several spatial and temporal function features. In order to facilitate writer-independent signature analysis, these feature sets are subsequently converted into a dissimilarity-based representation by means of a suitable dichotomy transformation. The classification techniques utilised for signature modelling and verification include quadratic discriminant analysis (QDA) and support vector machines (SVMs). The major contributions of this study include two novel techniques aimed towards the construction of a robust writer-independent signature model. The first, a dynamic time warping (DTW) based dichotomy transformation for off-line signature representation, is able to compensate for reasonable intra-class variability by non-linearly aligning DRT-based projections prior to matching. The second, a writer-specific dissimilarity normalisation strategy, improves inter-class separability in dissimilarity space by considering only strictly relevant dissimilarity statistics when normalising the dissimilarity vectors belonging to a specific individual. This normalisation strategy is generic in the sense that it is equally applicable to both off-line and on-line signature model construction. The systems developed in this study are specifically aimed towards skilled forgery detection. System proficiency estimation is conducted using a rigorous experimental protocol. Several large signature corpora are considered. In both the off-line and on-line scenarios, the proposed SVM-based system outperforms the proposed QDA-based system. We also show that the systems proposed in this study outperform most existing systems that were evaluated on the same data sets. More importantly, when compared to state-of-the-art techniques currently employed in the literature, we show that the incorporation of the novel techniques proposed in this study consistently results in a statistically significant improvement in system proficiency.

Please refer to this item in SUNScholar by using the following persistent URL: http://hdl.handle.net/10019.1/98042
This item appears in the following collections: