Dynamic Handwritten Signature Verification Based on Statistical Quantization Mechanism

Blumenstein

Proceedings of the International Conference &Amp; Workshop on Emerging Trends in Technology - ICWET '11

2011

Signatures are extensively used as a means of personal verification. Manual signature-based authentication of a large number of documents is a very difficult and time consuming task. Consequently for many years, in the field of protected communication and financial applications, we have observed an explosive growth in biometric personal authentication systems that are closely connected with measurable physical unique characteristics (hand geometry, iris scan, finger prints or DNA) or behavioural features. Human signatures provide secure means for confirmation and authorization in legal documents. So nowadays, automatic signature verification becomes an essential component. In order to convey the stateof-the-art in the field to researchers, in this paper we present a survey of off-line signature verification systems.

Section: Introductionmentioning

confidence: 99%

Off-line signature verification systems

Blumenstein

Proceedings of the International Conference &Amp; Workshop on Emerging Trends in Technology - ICWET '11

2011

“…Results of the proposed method have been obtained using min_ fraction = 0.03 for SVC2004 and min_fraction = 0.04 for SUSIG, with global_min = 5 for both the databases. Ong et al [37] 2009 statistical quantisation mechanism (SQM), user-dependent threshold…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

Online signature verification using segment‐level fuzzy modelling

Ansari¹,

Hanmandlu²,

Kour³

et al. 2014

IET biom.

This study presents a new online signature verification system based on fuzzy modelling of shape and dynamic features extracted from online signature data. Instead of extracting these features from a signature, it is segmented at the points of geometric extrema followed by the feature extraction and fuzzy modelling of each segment thus obtained. A minimum distance alignment between the two samples is made using dynamic time warping technique that provides a segment to segment correspondence. Fuzzy modelling of the extracted features is carried out in the next step. A user-dependent threshold is used to classify a test sample as either genuine or forged. The accuracy of the proposed system is evaluated using both skilled and random forgeries. For this, several experiments are carried out on two publicly available benchmark databases, SVC2004 and SUSIG. The experimental results obtained on these databases demonstrate the effectiveness of this system.

“…The online dynamic signature verification system that employs a set of 49 normalized features that tolerates inconsistencies in a genuine signature and retains the power to distinguish forgeries is explained in [22]. The statistical quantization mechanism that mitigates subtle intra-class variations in signature features to distinguish the differences between genuine and fake signatures is described in [23].…”

Section: Related Researchmentioning

confidence: 99%

Surgery Agreement Signature Authentication System for Mobile Health Care

Huh

2020

Electronics

Currently, the use of biometric systems is increasing following the increase in the non-face-to-face security transactions in the Health Care sector, where smart devices are extensively used. Additionally, hospital patients or their guardians had to sign every medical/surgery consent form with a pen. Currently, hospitals are attempting to digitalize the form to avoid its loss or delay to the operating room. Thus, this study proposes a surgery consent signature authentication system for the mobile health care system. Along with the vein or the fingerprint recognition technology, the smart electronic signature recognition technology is regarded as a new type of security solution for Mobile Health Care, which is a compound of Health Care and technology, or a smart contents and display technology. Thus, this study proposes a surgery agreement signature authentication system for Mobile Health Care while using the techniques, such as database segment units comparison in the cloud, Bag of Word, etc. The proposed system was implemented with Java language and developed in a way the reference signature stored in advance in a cloud database to be compared with the signature currently entered. For the comparison, the segment matching, spatial pyramid matching, and boundary matching techniques were used in addition to the Dynamic Time Warping (DTW) algorithm. Additionally, the system has been made lighter than the existing experimental products, so that it is easier to embed the system into a smart phone, tablet, or others. The Test Bed experiment result showed that the system operated flexibly.