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

arXiv: https://arxiv.org/abs/2204.03992 · HTML: https://mlsanity.com/paper/2204.03992/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 57 references that are in the map.
- First posted on arXiv 8 Apr 2022.

## Builds on (most cited first, 8 of 8)

- [Learning One Class Representations for Face Presentation Attack Detection using Multi-channel Convolutional Neural Networks](https://mlsanity.com/paper/2007.11457/) (2020)
- [Presentation Attack Detection for Iris Recognition: An Assessment of the State of the Art](https://mlsanity.com/paper/1804.00194/) (2018)
- [BioTouchPass2: Touchscreen Password Biometrics Using Time-Aligned Recurrent Neural Networks](https://mlsanity.com/paper/2001.10223/) (2020)
- [A Survey of Privacy Vulnerabilities of Mobile Device Sensors](https://mlsanity.com/paper/2106.10154/) (2021)
- [Biometric Presentation Attack Detection: Beyond the Visible Spectrum](https://mlsanity.com/paper/1902.11065/) (2019)
- [Mobile Touchless Fingerprint Recognition: Implementation, Performance and Usability Aspects](https://mlsanity.com/paper/2103.03038/) (2021)
- [Deep GAN-Based Cross-Spectral Cross-Resolution Iris Recognition](https://mlsanity.com/paper/2108.01569/) (2021)
- [GaitPrivacyON: Privacy-Preserving Mobile Gait Biometrics using Unsupervised Learning](https://mlsanity.com/paper/2110.03967/) (2021)

## Built on by (most cited first, 15 of 15)

- [ECG Semantic Integrator (ESI): A Foundation ECG Model Pretrained with LLM-Enhanced Cardiological Text](https://mlsanity.com/paper/2405.19366/) (2024)
- [Exploring Transformers for Behavioural Biometrics: A Case Study in Gait Recognition](https://mlsanity.com/paper/2206.01441/) (2022)
- [IJCB 2022 Mobile Behavioral Biometrics Competition (MobileB2C)](https://mlsanity.com/paper/2210.03072/) (2022)
- [Federated Learning and Differential Privacy Techniques on Multi-hospital Population-scale Electrocardiogram Data](https://mlsanity.com/paper/2405.00725/) (2024)
- [A Comprehensive Re-Evaluation of Biometric Modality Properties in the Modern Era](https://mlsanity.com/paper/2508.13874/) (2025)
- [ECG-Based Patient Identification: A Comprehensive Evaluation Across Health and Activity Conditions](https://mlsanity.com/paper/2302.06529/) (2023)
- [Verification and Identification in ECG biometric on large-scale](https://mlsanity.com/paper/2602.02776/) (2026)
- [ECG-Lens: Benchmarking ML & DL Models on PTB-XL Dataset](https://mlsanity.com/paper/2604.15822/) (2026)
- [ElectroCardioGuard: Preventing Patient Misidentification in Electrocardiogram Databases through Neural Networks](https://mlsanity.com/paper/2306.06196/) (2023)
- [Maximum diversity and weighting for invariants of periodic time series](https://mlsanity.com/paper/2509.11146/) (2025)
- [ECG Biometrics with ArcFace-Inception: External Validation on MIMIC and HEEDB](https://mlsanity.com/paper/2604.04485/) (2026)
- [ECG-biometrics-bench: A Unified Framework for Reproducible Benchmarking of ECG Biometrics](https://mlsanity.com/paper/2605.01548/) (2026)
- [Attention-Guided Fusion of 1D and 2D CNNs for Robust ECG-Based Biometric Recognition](https://mlsanity.com/paper/2605.17685/) (2026)
- [Learning Cardiac Features: ECG Biometrics Across Time and~Exercise](https://mlsanity.com/paper/2609.21962/) (2026)
- [From ECG Signals to Representative-Morphology Heatmaps for Biometric Recognition](https://mlsanity.com/paper/2609.28183/) (2026)

## Abstract (arXiv)

Electrocardiograms (ECGs) have shown unique patterns to distinguish between different subjects and present important advantages compared to other biometric traits, such as difficulty to counterfeit, liveness detection, and ubiquity. Also, with the success of Deep Learning technologies, ECG biometric recognition has received increasing interest in recent years. However, it is not easy to evaluate the improvements of novel ECG proposed methods, mainly due to the lack of public data and standard experimental protocols. In this study, we perform extensive analysis and comparison of different scenarios in ECG biometric recognition. Both verification and identification tasks are investigated, as well as single- and multi-session scenarios. Finally, we also perform single- and multi-lead ECG experiments, considering traditional scenarios using electrodes in the chest and limbs and current user-friendly wearable devices. In addition, we present ECGXtractor, a robust Deep Learning technology trained with an in-house large-scale database and able to operate successfully across various scenarios and multiple databases. We introduce our proposed feature extractor, trained with multiple sinus-rhythm heartbeats belonging to 55,967 subjects, and provide a general public benchmark evaluation with detailed experimental protocol. We evaluate the system performance over four different databases: i) our in-house database, ii) PTB, iii) ECG-ID, and iv) CYBHi. With the widely used PTB database, we achieve Equal Error Rates of 0.14% and 2.06% in verification, and accuracies of 100% and 96.46% in identification, respectively in single- and multi-session analysis. We release the source code, experimental protocol details, and pre-trained models in GitHub to advance in the field.