Beat-ID: Towards a Low-Computational Cost Single Heartbeat Biometric Identity Check System Based on Electrocardiogram Wave Morphology
In the past years, efforts were made to develop safer and more reliable biometric methods, for different applications. Beyond security, the media and entertainment sectors have been also applying biometrics for an emerging market of user-adaptable objects/systems within the field of Internet of Things (IoT). However, the associated complexity of some state-of-the-art biometric systems (e.g. iris recognition) or high False Rejection Rate (e.g. fingerprint recognition) are not compatible with the simple hardware architecture required by reduced size and newly trend smart objects. Recently, evidences that it is possible to recognize a person with good performance by extracting features from individuals electrocardiogram (ECG) were found. However, the majority of current ECG-based biometric algorithms are computationally demanding and/or rely on relatively large (several seconds) ECG samples, being therefore complex and not compatible with such application fields.
In this project, we are developing a low-computational cost method for identifying a person through only three ECG morphology-based characteristics from a single heartbeat which includes simple mathematical operations able to be embedded in a simple hardware module.
- Cunha JPS, Paiva JS. Biometric Method and Device for Identifying a Person Through an Electrocardiogram (ECG) Waveform – ref. PT109357; 2016 [Patent pending].
- Paiva JS, Dias D. Beat-ID: Towards a computationally low-cost single heartbeat biometric identity check system based on electrocardiogram wave morphology; PLoS ONE (in second revision); 2017.