Representative morphology heatmaps boost ECG biometric recognition accuracy
From ECG Signals to Representative-Morphology Heatmaps for Biometric Recognition
Computer Vision and Pattern Recognition
Summary
Electrocardiogram signals have unique shapes for each person that can be used to recognize them. The authors created a new way to turn these signals into images called representative-morphology heatmaps. These heatmaps preserve important details better than traditional waveform images and help computer models identify people more accurately. Testing on several datasets showed their method reduces recognition errors and improves identification rates. This approach could enhance security systems that use heart signals as biometric IDs.
What this means in practice
- •For biometric system developers: Improve ECG-based identity verification by using representative-morphology heatmaps for more accurate heartbeat image input.
- •For medical device engineers: Enhance patient authentication in medical monitoring devices by integrating heatmap representations of ECG signals.
- •For security solution providers: Develop novel security products that use improved ECG biometric images for stronger user identification.$Commercial implications: Enables commercialization of ECG biometric authentication devices with improved performance for security companies.
Authors
Athanasios Angelakis, Marta Gomez-Barrero
Abstract
Electrocardiography (ECG) contains subject-specific morphology that supports biometric recognition, yet image-based performance depends on how the waveform is rendered. We introduce representative-morphology heatmaps, a deterministic ECG-to-image representation adapted from ECGXtractor. Within each block of ten aligned beats, the five beats closest to the block mean are averaged into a 400 by L matrix and rendered either as a conventional trace or as a dense cardiac-time-by-lead heatmap. Since both representations contain identical physiological samples, their comparison isolates the effect of rendering. We evaluate verification and closed-set identification on PTB, ECG-ID, and MIMIC-IV-ECG-DEMO. Five compact models, including ZACH-ViT, are trained from scratch, while six ImageNet-pretrained CNN and transformer backbones assess model scale and visual transfer. Heatmaps improve both FNMR operating points and both identification ranks in all 15 compact model-dataset comparisons, while EER improves in 14. Across the matched experiments, EER decreases by 9.59 percentage points and Rank-1 increases by 24.69 points on average. ConvNeXt-Tiny reaches 2.43% EER on PTB and 5.79% on ECG-ID, whereas DeiT-Base reaches 14.92% on MIMIC-DEMO. ImageNet initialization clearly benefits the two multilead datasets but has a mixed effect on ECG-ID, and performance does not increase monotonically with model size. The best heatmap systems approach the strongest signal-domain EER on PTB and ECG-ID, while DeiT-Base provides the strongest evaluated performance on MIMIC-DEMO. Lead-channel ablation further shows that useful channel combinations depend on the cohort and biometric task. Overall, representative-morphology heatmaps provide an effective image representation for ECG verification and identification.