Time/Space based Biometric Handwritten Signature Verification

• Type: Article in International Conference Proceedings Book
• Date: 2015

Authors

Goncalves, RP (Author) Other; Augusto, AB (Author) Other; Manuel E Correia (Author) FCUP

Conference proceedings International

Title: 2015 10TH IBERIAN CONFERENCE ON INFORMATION SYSTEMS AND TECHNOLOGIES (CISTI)

10th Iberian Conference on Information Systems and Technologies (CISTI)

Univ Aveiro, Sch Technol & Agueda Management, Agueda, PORTUGAL, JUN 17-20, 2015

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 0 Citations

Scientific classification

CORDIS: Technological sciences > Engineering > Computer engineering

FOS: Natural sciences > Computer and information sciences

Other information

Authenticus ID: P-00G-PWG

DOI: 10.1109/cisti.2015.7170483

Abstract (EN): Handwritten signature recognition is still the most widely accepted method to validate paper based documents. However, in the digital world, there is no readymade way to distinguish a real handwritten signature on a scanned document from a forged copy of another signature made by the same person on another document that is simply "pasted" into the forged document. In this paper we describe how we are using the touch screen of smartphones or tablets to collect handwritten signature images and associated biometric markers derived from the motion direction of handwritten signatures that are made directly into the device touchscreen. These time base biometric markers can then be converted into signaling time waves, by using the dragging or lifting movements the user makes with a touch screen omnidirectional tip stylus, when he handwrites is signature at the device touchscreen. These time/space signaling time waves can then be converted into a biometric bit stream that can be matched with previously enrolled biometric markers of the user's handwritten signature. In this paper we contend that the collection of these simple biometric features is sufficient to achieve a level of user recognition and authentication that is sufficient for the majority of online user authentication and digital documents authenticity.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 6