| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 1.91 MB | Adobe PDF |
Advisor(s)
Abstract(s)
Behavioral biometrics is one of the areas with growing interest within the biosignal research community. A recent trend in the field is ECG-based biometrics, where electrocardiographic (ECG) signals are used as input to the biometric system. Previous work has shown this to be a promising trait, with the potential to serve as a good complement to other existing, and already more established modalities, due to its intrinsic characteristics. In this paper, we propose a system for ECG biometrics centered on signals acquired at the subject's hand. Our work is based on a previously developed custom, non-intrusive sensing apparatus for data acquisition at the hands, and involved the pre-processing of the ECG signals, and evaluation of two classification approaches targeted at real-time or near real-time applications. Preliminary results show that this system leads to competitive results both for authentication and identification, and further validate the potential of ECG signals as a complementary modality in the toolbox of the biometric system designer.
Description
Keywords
Biometric systems ECG signal Real time recognition systems SVM classifiers
Citation
LOURENÇO, André; SILVA, Hugo; FRED, Ana – ECG-based biometrics: A real time classification approach. In 2012 IEEE International Workshop on Machine Learning for Signal Processing. Santander, Spain: IEEE, 2012. ISBN: 978-1-4673-1026-0. Pp. 1-6.
Publisher
IEEE