ECG Biometric Recognition: Review, System Proposal, and Benchmark Evaluation

ECGs have shown unique patterns to distinguish between different subjects and present important advantages compared to other biometric traits. However, the lack of public data and standard experimental protocols makes the evaluation and comparison of novel ECG methods difficult. In this study, we perform extensive analysis and comparison of different scenarios in ECG biometric recognition. We consider verification and identification tasks, single- and multi-session settings, and single- and multi-lead ECGs recorded with traditional and user-friendly devices. We also present ECGXtractor, a robust Deep Learning technology trained with an in-house large-scale database, and evaluate it with detailed experimental protocol and public databases. With the popular PTB database, we achieve Equal Error Rates of 0.14% and 2.06% in single- and multi-session verification. The results achieved prove the soundness of ECGXtractor across multiple scenarios and databases. We release the source code, experimental protocol details, and pre-trained models in GitHub to advance in the field.

Automated summary

ECGs have unique patterns that can distinguish between different individuals and offer significant advantages over other biometric traits. However, the lack of public data and standardized experimental protocols makes it difficult to evaluate and compare novel ECG methods. In this study, we extensively analyze and compare various scenarios in ECG biometric recognition, including verification and identification tasks, single- and multi-session settings, and traditional and user-friendly devices. We also introduce ECGXtractor, a robust Deep Learning technology trained with a large-scale in-house database, and evaluate it using detailed experimental protocols and public databases. Our results demonstrate the effectiveness of ECGXtractor across multiple scenarios and databases, achieving low Equal Error Rates in single- and multi-session verification. We provide the source code, experimental protocol details, and pre-trained models on GitHub to facilitate further research in this field.