Face-based Passive Customer Identification Combined with Multimodal Context-aware Payment Authorization: Evaluation at Point of Sale

Adam Wójtowicz , Jacek Chmielewski


In smart environments, fast passive transaction authorization is a key requirement for routine, recurring transactions. In our earlier work technical feasibility of multimodal multidevice system based on context-aware payment authorization model has been proved. Its main features are: passive user identification with face recognition followed by multi-criteria selection of transaction authorization methods, which jointly modify traditional customer service procedure. In the presented work, real-world evaluation of the new approach based on proposed multimodal payment authorization is described. Empirical tests at existing point of sale have been performed, the usage data have been collected, statistically analyzed and confronted with formulated research hypotheses. The research goal is to determine to what extent the approach simplifies payment process assuming the security level required for a given context is maintained. The evaluation confirms that proposed approach can be effectiv e in a real environment.
Author Adam Wójtowicz (WIiGE / KTI)
Adam Wójtowicz,,
- Department of Information Technology
, Jacek Chmielewski (WIiGE / KTI)
Jacek Chmielewski,,
- Department of Information Technology
Publication size in sheets0.55
Book Hammoudi Slimane, Śmiałek Michał, Camp Oliver, Filipe Joaquim (eds.): Proceedings of the 20th International Conference on Enterprise Information Systems, vol. 1, 2018, Institute for Systems and Technologies of Information, Control and Communication (INSTICC), ISBN 978-989-758-298-1, 742 p.
Keywords in Englishcontext-aware authorization, payment authorization, passive identification, multimodal authorization, face recognition
URL http://www.scitepress.org/PublicationsDetail.aspx?ID=SY+yUHHWs1w=&t=1
Languageen angielski
Score (nominal)20
Score sourceconferenceList
ScoreMinisterial score = 20.0, 23-04-2020, ChapterFromConference
Citation count*1 (2020-09-12)
Share Share

Get link to the record

* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Are you sure?