ECG Biometrics: Principles and Applications

Hugo Silva

, Andr

e Lourenc¸o

1,2

, Filipe Canento

, Ana Fred

and Nuno Raposo

Instituto de Telecomunicac¸

oes, IST-UTL, Lisbon, Portugal

DEETC, ISEL-IPL, Lisbon, Portugal

Escola Superior de Sa

ude, Cruz Vermelha Portuguesa, Lisbon, Portugal

Keywords:

Electrocardiography, Identity Recognition, Biometrics, Biosignal Processing.

Abstract:

Electrocardiographic (ECG) signals have several properties that can greatly complement the existing, and more

established biometric modalities. Some of the most prominent properties are the fact that the signals can be

continuously acquired using minimally intrusive setups, are not prone to produce latent patterns, and provide

intrinsic liveliness detection, opening new opportunities within the area of biometric systems development.

The potential impact of this technique extends to a broad variety of application domains, ranging from the

entertainment industry, to digital transactions. In this paper, we present a framework for ECG biometrics,

with focus on some of the latest developments and future trends in the ﬁeld, covering multiple aspects of

the problem with the aim of a real-world deployment. Our results so far, further reinforce the feasibility and

interest of the method in a multibiometrics approach.

1 INTRODUCTION

Biometrics is an increasingly growing multibillion

dollar market; a recent report by Global Industry An-

alysts, Inc. (Global Industry Analysts, 2011), esti-

mates that by 2017 revenues will grow above $16 bil-

lion USD.

User recognition techniques, either in an authen-

tication or identiﬁcation framework, are generally

classiﬁed according to their operating principle (Jain

et al., 2011), namely: a) What the person knows (e.g.

passwords); b) What the person has (e.g. identity

card); c) What the person appears to be (e.g. face);

and d) What the person does (e.g. voice). The later

two methods are generally framed in the area of bio-

metric recognition which, in the current state-of-the-

art, includes different types of physical (e.g. ﬁnger-

print or iris) and behavioral traits (e.g. signature or

keystroke dynamics), among others.

Despite the fact that biometric systems are highly

advantageous for user recognition, as they provide in-

formation which is more directly related to intrinsic

characteristics of the individual, most of the traits cur-

rently in use today are only practical for momentary,

single validation recognition operations, within a rea-

sonably large time frame. For example, techniques

that rely on the ﬁngerprint and/or hand geometry, re-

quire the user to place or pass the ﬁnger and/or hand

in a speciﬁc way through a physical reader; tech-

niques that rely on the iris, require the user to stand in

a speciﬁc physical space, and to have the eye in line

of sight with the reader; these and other constraints

ultimately limit the scope of application.

The unique properties of ECG signals, are particu-

larly interesting in a multibiometrics approach, either

as a security enhancement layer in hard biometrics

systems, or as a standalone soft biometrics for low

security and low user throughput applications. More

importantly, as it can be continuously measured, it

enables a new class of applications beneﬁtting from

the continuous biometric perspective. In this paper

we present a framework for ECG biometrics, cover-

ing the essential building blocks; experimental results

have been performed, which further reinforce the in-

terest of the ECG-based methods both in an identiﬁ-

cation and authentication approach.

The remainder of the paper is organized as fol-

lows. Sections 2 and 3, present a brief overview of the

state-of-the-art and base principles of Electrocardio-

graphy (ECG). The proposed approach is described

throughout Sections 4, 5, and 6, where the sensor

design, signal processing, and biometric recognition

steps are presented. Experimental results are summa-

rized in Section7, and ﬁnally we highlight discussion

topics and outline the main conclusions in Sections 8

and 9.

215

Silva H., Lourenço A., Canento F., Fred A. and Raposo N..

ECG Biometrics: Principles and Applications.

DOI: 10.5220/0004243202150220

In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS-2013), pages 215-220

ISBN: 978-989-8565-36-5

 2013 SCITEPRESS (Science and Technology Publications, Lda.)

Figure 1: Waveforms of each specialized cells found in the

heart (Malmivuo and Plonsey, 1995).

2 STATE-OF-THE-ART

Recent work has been devoted to the characterization

of ECG features for human identiﬁcation, and exper-

imental results have highlighted their discriminating

capacity. Still, studies have focused on the ofﬂine pro-

cessing of clinical-grade ECG in an on-the-person ap-

proach, with multiple measurement leads. Biel et al.

(Biel et al., 2001) were precursors in the ﬁeld; in their

initial work a 12-lead setup was used, and with 10

ﬁducial features the authors reported 100% accuracy

in identiﬁcation for a population of 20 subjects.

Shen et al. (Shen et al., 2002) experimented on

a group of 20 subjects from the MIT/BIH database

(Goldberger, A. et al., 2000); they achieved 100% ac-

curacy using a combination of template matching and

neural networks. Other experiments were performed

by (Israel et al., 2005) on data from 29 subjects; sig-

nals were collected at the chest and neck, and 12 la-

tency and amplitude features were used. Using LDA,

individual waveforms are classiﬁed and mapped to the

identity of the subject by majority voting, leading to

100% identiﬁcation rates.

Research to date has mostly neglected the speci-

ﬁcities of real-world application scenarios and accept-

ability by the potential end users, which pose sev-

eral constraints and research questions. In the work

by (Silva et al., 2007), the authors have concluded

that a single lead setup sufﬁces; using a V

chest

placement, an identiﬁcation accuracy of 100% was

achieved. Later, a palmar placement has been shown

to perform accurately in the work by (Lourenc¸o et al.,

2011), where for a group of 16 users, even with con-

siderably noisier signals, recognition rates of 94.3%

for identiﬁcation and an Equal Error Rate (EER) of

10.1% are still achieved.

3 PRINCIPLES OF ECG

To accomplish its function, which is basically to

pump blood to the pulmonary and systemic circula-

tion, the heart generates electrical current, by the con-

traction of its muscle cells. Some of these are special-

ized; the conduction system. These cells have the ca-

pability of self-stimulation, which generates the car-

diac rhythm, usually a regular sequence of heart beats.

The electrical conduction system of the heart is

composed by the sinoatrial node (SA node) that nor-

mally initiates the cardiac cycle, the atrioventricular

node (AV node), the internodal atrial pathways, which

connect the two and regulate the passage of the car-

diac impulse from the atria to the ventricles, and the

bundle of His and corresponding branches, which in

turn are terminated by the Purkinje ﬁbers (Chung,

2000; Malmivuo and Plonsey, 1995). This system

enables the electrical triggering impulses generated

at the SA node, to be propagated from the wall of

the right atrium (where the SA node is located), to

the deeper tissues of the ventricular muscles (through

where the Purkinje ﬁbers are spread).

The ultimate result of this overall bioelectrical ac-

tion is the heartbeat. Figure 1 depicts the contribu-

tion of each specialized group of cells to the heartbeat

waveform (Malmivuo and Plonsey, 1995). The de-

polarization of the atria generates an ECG wave (P

wave), followed by the QRS complex, which repre-

sents the ventricular contraction. The end of the car-

diac cycle is the cell repolarization phase, which ap-

pears as another deﬂection, the T wave; in some cases,

the a second deﬂection may appear, the U wave.

When measured non-invasively, the ECG records

the combined contribution of each component of the

electrical conduction system, as propagated to the

body surface, and which is expressed as the typical

P-QRS-T complexes; this effect alone favors the ex-

istence of subject-dependent information, due to the

size, shape, and position of the heart within the chest

cavity, which varies amongst individuals. However,

other factors such as tissue conductivity, genetic sin-

gularities, congenital disorders, and heart conditions,

constitute additional information sources.

Figure 2 illustrates the ECG while at rest, from

two different subjects without any reported heart con-

dition. The plotted individual waveforms y

were nor-

malized to the mean wave ¯x computed from the orig-

inal segmented heartbeat waveforms x

(eq. 2) and

clipped for better visual understanding. Both subjects

BIOSIGNALS2013-InternationalConferenceonBio-inspiredSystemsandSignalProcessing

216

(a) (b)

Figure 2: Electrocardiographic recordings from two differ-

ent subjects while at rest, where the time series were pro-

cessed to extract one hundred individual heartbeat wave-

forms, which were then clipped and scaled to ﬁt to the

same XX and YY axis limits for better comparison. Fig-

ures 2(b) and 2(c) depict the individual waves overlapped,

with a solid line representing the mean wave, and a dashed

line representing the standard deviation. Figures 2(a) and

2(d) depict a color-map plot, where each line corresponds

to an individual heartbeat wave form, and each column rep-

resents the amplitude value of a sample; in the color-map,

the signal was smoothed around the R peak to enhance the

color intensities in the remaining signal.

exhibit morphologically distinct waveforms, with a

low intersubject variability; the intensity map of the

segmented heartbeat waveforms, showing their tem-

poral evolution, further enhances the differences.

¯x =

∑

i=1

(1)

− min( ¯x)

max( ¯x) − min( ¯x)

(2)

Amongst other singularities, in these two cases,

the P-Q and S-T curves and latency are signiﬁcantly

distinct; the relative amplitude P-T also varies be-

tween subjects. Comparing the ECG of Subject A and

B, we observe for example that the bundle branches

and Purkinje ﬁbers have a lower activation amplitude

in Subject B, or that the AV node recovery time is

lower in Subject A.

The fact that there are subject dependent features

in the ECG, enhances its applicability for user recog-

nition. Furthermore, the ECG has unique properties

when looked at in a multibiometrics approach; in par-

ticular, it is: a) universally available in live subjects;

b) measurable non-intrusively using suitable devices;

c) acceptable due to the latest advances in the sens-

ing technologies; d) not easily circumvented through

latent patterns.

4 SENSOR DESIGN

Conventional clinical-grade ECGs are acquired using

12 or more leads mounted on the chest and limbs, us-

ing conductive paste or gel to lower the electrode/skin

impedance. Part of our work has focused on extend-

ing the state-of-the-art, improving current methods by

developing a sensor for signal acquisition at the hand

palms or ﬁngers. We focused on minimizing the num-

ber of electrical contact points with the subject’s body,

eliminating the need for any gel or conductive paste

in the interface with the skin, and devising a non-

intrusive sensor design for wearable devices and end-

user applications.

A pseudo V

bipolar sensor with virtual ground

and dry electrodes was created, consisting of: a) a

differential ampliﬁer with gain 10, input impedance

> 1MΩ, and 110dB CMRR; b) two passive analog

ﬁltering steps composed by a [0.05;100]Hz band pass

ﬁlter, and a notch ﬁlter to cut off the 50Hz power

line interference; and c) a second ampliﬁcation stage

with gain 100 to obtain higher resolution from the col-

lected signal. The sensor has only two contact points

with the subject, and works with standard pre-gelled,

dry Ag/AgCl, or conductive textile electrodes.

Experimental results have shown that this setup

provides an adequate signal quality and biometric per-

formance, even when compared with a more tradi-

tional chest setup (Silva et al., 2011; Lourenc¸o et al.,

2011). In the overall, we follow a novel off-the-

person approach, thus making the usability and intru-

siveness comparable to the one found in other bio-

metric traits (e.g. ﬁngerprint). Figure 3 shows the

prototype sensor, which can be used as a standalone

module, or integrated into everyday objects.

5 SIGNAL PROCESSING

5.1 Filtering

As measured at the body surface, ECG signals are af-

fected by multiple noise sources such as motion arti-

facts, and power line or electromyographic noise; this

aspect is event more challenging in the proposed off-

the-person approach, where the impedance between

the electrode and the skin is signiﬁcantly higher due

to the lack of gel. We designed a digital zero-phase

forward and reverse Butterworth band pass ﬁlter with

1 − 30Hz cutoff frequencies, to limit the bandwidth

ECGBiometrics:PrinciplesandApplications

217

(a) Standalone module. (b) Computer panel.

Figure 3: Sensor integration possibilities of the proposed

approach.

of the raw data. Note that whereas for clinical appli-

cations, a larger passing band is required to preserve

additional ﬁducia, for biometrics we can optimize the

ﬁltering taking into account the recognition accuracy.

5.2 Segmentation

Our classiﬁer is based on template matching, using

the informative content of the heartbeat waveforms,

and as such, a compatible real-time segmentation al-

gorithm is adopted. We build on the work by (En-

gelse and Zeelenberg, 1979) for ofﬂine QRS detec-

tion, and propose a combination strategy that uses

adaptive thresholds estimated along the acquisition

process, according to the methodology and estimation

scheme described in (Christov, 2004; Christov and

Stoyanov, 2002). A comprehensive description of our

proposed approach and comparison between ofﬂine

and real-time approaches can be found in (Lourenc¸o

et al., 2012), where the proposed real-time approach

has shown to be competitive. On the ECG biometric

point of view, these algorithms represent an important

contribution towards the real-world deployment.

6 BIOMETRIC RECOGNITION

6.1 Feature Extraction

All segmented heartbeat waveforms are aligned by

their R-peak, and clipped taking into account the typ-

ical physiological latencies between the P-R and R-

T complexes, which are approximately 200 and 400

milliseconds respectively (Chung, 2000). In this pa-

per, the feature vector for each heartbeat waveform

i, consists of a vector x

with the waveform ampli-

tude values, which corresponds to 600ms of collected

signal. During the enrollment stage, the patterns x

are stored in the database of known users, whereas

in the recognition stage, it is the pattern which will

be checked against the database. Depending on the

latency requirements of the application, we can also

use an average of m feature vectors, which is prone to

further improve the recognition rates.

6.2 Classiﬁcation

We use an instance-based learning, template matching

approach, through a 1-NN classiﬁer, by computing

the similarity between the feature vectors x

extracted

in the recognition phase, and the ones extracted and

stored on the enrollment phase, x

. The decision on a

genuine/impostor (authentication task), is determined

by verifying if the Euclidean distance D(x

, x

), is

below an acceptance threshold, computed from the

database of enrolled users. For identiﬁcation, the

dissimilarities between the observed pattern x

and

the templates from all enrolled users are computed,

and the user identity ˆw

is estimated as the class w

corresponding to the pattern x

with lower distance

D(x

, x

), that is, ˆw

= w

: i = argmin

(D(x

, x

)).

7 EXPERIMENTAL EVALUATION

Tests were performed on 32 healthy individuals (25

males) with 31.1±9.46 years, using the proposed sen-

sor setup. Subjects were asked to rest their left/right

hands over the sensor leads, and data was acquired

during a period of approximately 1m30s, during

which the experiment supervisor explained the pur-

pose of the study. Raw signals were processed ac-

cording to the proposed approach, separated into a

training set with 30% of the total collected patterns,

and a test set with the remaining 70% of the patterns.

We evaluated the user recognition potential of

ECG signals collected at the hand palms using di-

rectly the individual heartbeat waveforms directly,

and also the mean waves computed from a variable

number, m, of waveforms. The template matching

technique is extremely lightweight in terms of real-

time processing, and the mean waves reduce the pat-

tern variability, which is particularly suitable in a real-

time framework.

BIOSIGNALS2013-InternationalConferenceonBio-inspiredSystemsandSignalProcessing

218

Figure 4: ROC curve for the m = 5 best case scenario; m de-

notes the number of waves used to compute the mean wave.

Table 1 shows the Equal Error Rate (EER) for au-

thentication and Identiﬁcation Error (EID) varying the

number of patterns m used on the computation of the

mean waves. When individual heartbeat waveforms

are used, a mean EER of 9.39% ± 0.19 is obtained

in authentication, which decreases to 2.75% ± 0.29

when averages of 5 waveforms are used; for identiﬁ-

cation, a mean EID of 17.62% ± 0.59 is obtained us-

ing individual heartbeat wave forms, which decreases

to 5.61% ± 0.94, when averages of 5 waveforms are

used. The 1 and 5 heartbeats cases correspond, re-

spectively, to 1s and 5s of acquired signals. The

Receiver Operating Characteristics (ROC) curve for

the m = 5 best case scenario, is presented in Figure 4.

Our results hold comparable performance when

matched to other modalities; even when compared to

previous ECG based approaches. Table 2, summa-

rizes the user recognition results typically found in

the literature for other biosignal based modalities (see

(Gamboa, 2008) and references therein). Although

the traditional V

ECG lead approaches achieve higher

accuracy levels, our results, besides holding compa-

rable results, also provide a good compromise be-

tween performance and acceptability. Our experi-

mental setup provides usability levels similar to those

found in the most widespread modalities, and can be

easily integrated into everyday use devices without

impacting on the users normal activities, potentiating

its use in a continuous biometrics framework.

8 DISCUSSION

Experimental evaluation with real-world data, has re-

vealed an EER of 2.75% ±0.29 in authentication and

5.61% ± 0.94 EID in identiﬁcation within a group of

32 subjects. Our system can be further optimized de-

Figure 5: Example of signals collected on two different mo-

ments in time (approximately 4 months appart).

Figure 6: Experimental hardware and software prototype.

pending on the application scenarios. In our previous

paper (Silva et al., 2012), a variation of the proposed

approach was used to evaluate the applicability of our

method to in-vehicle driver recognition. An impor-

tant aspect within ECG biometric systems, which has

been marginally covered in the state-of-the-art is the

stability of the signals over time. Preliminary results

from our work have shown that, in similar acquisi-

tion conditions, the heartbeat waveforms retain a great

part of their informative content over time. Figure 5,

shows an example of two heartbeat waveforms col-

lected with a 4 months interval in one test subject; the

waves are normalized by the maximum and minimum

value for easier comparison, and as we can observe,

both show a high morphological resemblance.

ECGBiometrics:PrinciplesandApplications

219

Table 1: EER and EID for the proposed approach over 30 runs where exclusive training and test sets were randomly selected.

m 1 2 3 4 5

EER 9.39% ±0.19 6.05% ±0.36 4.55% ±0.41 3.13% ±0.41 2.75% ±0.29

EID 17.62% ±0.59 11.94% ±0.96 8.71% ±0.85 6.72% ±0.82 5.61% ±0.94

Table 2: EER for other behavioral biometric approaches.

Method Key Stroke Mouse Voice Gait Eye Gaze EEG ECG V

EER ∼ 4% ∼ 10% ∼ 10% ∼ 5% ∼ 5% ∼ 10% ∼ 5%

9 CONCLUSIONS

In this paper we have presented an overview of the

base principles and applications of ECG biometrics.

If we analyze the ECG in a multibiometrics perspec-

tive, it sets an important ground for novel biomet-

ric applications, especially those related to continu-

ous user recognition. Results so far are encouraging,

which have led us to create an initial prototype sys-

tem (Figure 6). Immediate applications of our tech-

nology include scenarios of low security and low user

throughput, such as recognition in mobile phones,

laptop computers, cable TV interfaces, and user-tuned

in-game experience. If combined with other modali-

ties, there are several use cases where the ECG stands

as an important add-on. For example high security

applications, we can envision scenarios where user

recognition is periodically performed using a hard

biometrics such as the ﬁngerprint, ECG data is col-

lected simultaneously with the ﬁngerprint to extract

a heartbeat waveform template, and after the initial

identity validation using the hard biometric modality,

the ECG continues to enable the validation of the user.

ACKNOWLEDGEMENTS

This work was funded by Fundac¸

ao para a

encia e Tecnologia (FCT) under the grants

SFRH/BD/65248/2009 and SFRH/PROTEC/49512/

2009, and by the Instituto de Telecomunicac¸

oes un-

der the grant ”Android Biometric System”.

REFERENCES

Biel, L., Petterson, O., Phillipson, L., and Wide, P. (2001).

ECG analysis: A new approach in human identiﬁca-

tion. IEEE Transactions on Instrumentation and Mea-

surement, 50(3):808–812.

Christov, I. I. (2004). Real time electrocardiogram QRS

detection using combined adaptive threshold. Biomed

Eng Online, 3(1).

Christov, I. I. and Stoyanov (2002). Steep slope method

for real time QRS detection. Electrotechniques and

Electronics, pages 13–17.

Chung, E. K. (2000). Pocketguide to ECG Diagnosis.

Blackwell Publishing Professional.

Engelse, W. A. H. and Zeelenberg, C. (1979). A single scan

algorithm for QRS-detection and feature extraction.

Comp. in Cardiology, 6:37–42.

Gamboa, H. (2008). Multi-Modal Behavioural Biometrics

Based on HCI and Electrophysiology. PhD thesis,

IST-UTL.

Global Industry Analysts, I. (2011). Biometrics - a global

strategic business report. T. Rep. GIA, Inc.

Goldberger, A. et al. (2000). PhysioBank, physiotoolkit,

and physionet: Comp. of a new research res. for com-

plex physiologic signals.

Israel, S., Irvine, J., Cheng, A., Wiederhold, M., and

Wiederhold, B. (2005). ECG to identify individuals.

Pattern Recognition, 38(1):133–142.

Jain, A. K., Ross, A. A., and Nandakumar, K. (2011). In-

troduction to Biometrics. Springer.

Lourenc¸o, A., Silva, H., and Fred, A. (2011). Unveiling

the biometric potential of Finger-Based ECG signals.

Comp. Intell. and Neuroscience, 2011.

Lourenc¸o, A., Silva, H., Leite, P., Lourenc¸o, R., and Fred,

A. (2012). Real time electrocardiogram segmenta-

tion for ﬁnger based ECG biometric. In BIOSIGNALS

2012, pages 49–54.

Malmivuo, J. and Plonsey, R. (1995). Bioelectromagnetism:

Principles and Applications of Bioelectric and Bio-

magnetic Fields. Oxford Press.

Shen, T. W., Tompkins, W. J., and Hu, Y. H. (2002). One-

lead ECG for identity veriﬁcation. In Proc. of the

IEEE EMBS ’02 Conference.

Silva, H., Gamboa, H., and Fred, A. (2007). Applicability

of lead v2 ECG measurements in biometrics. In Proc.

of the Med-e-Tel Forum.

Silva, H., Lourenc¸o, A., and Fred, A. (2012). In-vehicle

driver recognition based on hand ECG signals. In

Proc. of the IUI ’12 Conf., IUI ’12.

Silva, H., Lourenc¸o, A., Lourenc¸o, R., Leite, P., Coutinho,

D., and Fred, A. (2011). Study and eval. of a sin-

gle differential sensor design based on electro-textile

electrodes for ECG biometrics applications. In Proc.

of the IEEE Sensors Conf.

BIOSIGNALS2013-InternationalConferenceonBio-inspiredSystemsandSignalProcessing

220