Kernel Deep Regression Network for Touch-Stroke Dynamics Authentication

• Published in: IEEE signal processing letters 2018-07, Vol.25 (7), p.1109-1113
• Main Authors: Chang, Inho, Low, Cheng-Yaw, Choi, Seokmin, Teoh, Andrew Beng-Jin
• Format: Article
• Language: English
• Subjects: Authentication; biometrics; Biometrics (access control); Feature extraction; Hidden Markov models; Kernel; Machine learning; stacking-based deep neural network; touch-stroke dynamics; Training
• ISSN: 1070-9908; 1558-2361
• DOI: 10.1109/LSP.2018.2846050

Touch-stroke dynamics is an emerging behavioral biometrics justified feasible for mobile identity management. A touch-stroke dynamics authentication system is composed of a hand-engineered feature extractor and a classifier separately. In this letter, we propose a stacking-based deep learning network that performs feature extraction and classification, collectively dubbed Kernel Deep Regression Network (KDRN). The KDRN is built on multiple kernel ridge regressions (KRR) hierarchically, where each is trained analytically and independently. In principal, KDRN does not mean to learn directly from the raw touch-stroke data like other deep learning models, but it relearns from the pre-extracted features to yield a richer and a relatively more discriminative feature set. Subsequent to that, the authentication is carried out by KRR. Overall, KDRN achieves an equal error rate of 0.013% for intrasession authentication, 0.023% for intersession authentication, and 0.121% for interweek authentication on the Touchlaytics dataset.