Visible to the public Hybrid Feature Extraction for Palmprint-Based User Authentication

TitleHybrid Feature Extraction for Palmprint-Based User Authentication
Publication TypeConference Paper
Year of Publication2018
AuthorsGiełczyk, Agata, Choraś, Michał, Kozik, Rafał
Conference Name2018 International Conference on High Performance Computing Simulation (HPCS)
Keywordsauthentication, authorisation, biometry, color information, Databases, Discrete Fourier transforms, feature extraction, Histograms, Human Behavior, human factors, hybrid feature extraction, image colour analysis, image texture, IT systems, Metrics, mobile computing, Mobile handsets, mobile verification scenarios, multifactor authentication, palmprint recognition, palmprint-based user authentication, pubcrawl, resilience, Resiliency, security, smart phones, smartphones, texture, user identity verification
AbstractBiometry is often used as a part of the multi-factor authentication in order to improve the security of IT systems. In this paper, we propose the palmprint-based solution for user identity verification. In particular, we present a new approach to feature extraction. The proposed method is based both on texture and color information. Our experiments show that using the proposed hybrid features allows for achieving satisfactory accuracy without increasing requirements for additional computational resources. It is important from our perspective since the proposed method is dedicated to smartphones and other handhelds in mobile verification scenarios.
DOI10.1109/HPCS.2018.00104
Citation Keygielczyk_hybrid_2018