Abstract
Biometrics refer to unique measurable characteristics and information regarding individual’s health, physical or mental condition and can be used to uniquely authenticate or verify a person’s identity. They can be sorted in physiological such as fingerprints, palm print, face recognition, iris recognition, retina and DNA and behavioral such as typing rhythm (i.e. signature) and voice and can be described based on the uniqueness, potential change with time (i.e. facial changes), the feasibility to be collected (i.e. fingerprints) and the purposes of usage. In this work we study the use of a biometric technology for eHealth. We present the SpeechXRays project initiative that aims to provide a solution combining the convenience and cost-effectiveness of face and voice biometrics, achieving better accuracies by combining it with video, and bringing superior anti-spoofing capabilities. We explain how a novel user interface biometric platform is designed and adapted, for an eHealth use case, to enable secure access for medical specialists, nurses and patients to a collaborative eHealth platform that provides access to clinical and health related data within and possible outside a hospital. This is the first study, in the field, that gathered all necessary requirements (for a voice/face biometric system) and provides a formative evaluation and implementation of the SpeechXrays system user interface, for both end users and administrators, following a user-centered design approach, based on the holistic consideration of the user experience and the technical implication and functional requirements of the platform.
Access provided by CONRICYT-eBooks. Download conference paper PDF
Similar content being viewed by others
Keywords
- Biometric authentication/verification
- Voice
- Acoustic
- User interface design
- Heuristic/guidelines
- Smartphone
- Mobile
- Internet of things
- Personal health systems
- eHealth/mHealth
1 Introduction
Biometrics refers to the automated recognition of individuals based on biological (i.e., face, fingerprint, iris, voice, DNA, etc.) or behavioural traits (i.e., keyword dynamics, signature, gait, etc.) [13]. Biometric authentication is a natural alternative to traditional authentication systems like password schemes and secure electronic identification cards that promises increased security and user convenience [1]. A typical biometric authentication involves two stages, the enrolment stage and the verification stage. During the enrolment, the system acquires a biometric trait of an individual (i.e., iris, fingerprint, face, voice, etc.), extracts a specific feature set from it and stores it in a database as a template. It then assigns an identifier associating the created template with an individual. During the verification stage, the system once again acquires the biometric trait of an individual, extracts a feature set from it, and compares it against the templates that are stored in the database in order to verify the claimed identity [11].
SpeechXRays aims to develop and test, in real-life environments, a user recognition platform based on voice acoustics analysis and audio-visual identity verification. The vision is to combine and pilot two multi-channel biometrics techniques: acoustic driven voice recognition (using acoustic and not statistical only models) and dynamic face recognition. SpeechXRays aims to outperform current state-of-the-art solutions in the areas of Security: high accuracy solution, Privacy: biometric data stored in the device, Cost-efficiency: use of standard embedded microphone and cameras (smartphones, laptops) and most importantly Usability: text-independent speaker identification (no pass phrase), low sensitivity to surrounding noise and state of the art User interface design for user interaction. Usability evaluation will be performed during the pilot of the two multi-channel biometrics techniques: acoustic driven voice recognition (using acoustic and not statistical only models) and dynamic face recognition in the project use cases involving 2000 users in 3 pilots: a workforce, an eHealth [23, 24] use case and a consumer use case. This paper describes the activities concerning the design, formative evaluation and implementation of the SpeechXrays system user interface, for both end users and administrators, following a user-centered design approach, based on the holistic consideration of the user experience and the technical implication and functional requirements of the platform. We present the methodology followed for the design of the user interfaces of the SpeechXRays system based on general usability and user interface requirements, as well as specific use cases requirements [22]. Based on this analysis several UI prototypes were designed and assessed following a formative usability evaluation approach. A mock up system was created to guide user interface development and integration to support UI adaptations as required by the SpeechxRays verification framework. Figure 1 presents the user interaction for the verification of medical personnel, for management of sensitive medial data such as medical information for patients, in the eHealth use case. We present a novel interface design methodology for interactive biometrics applications, taking into consideration all complex functional biometric processes and parameters, such as the scope/goal of the application, the functional and non-functional user requirements, the profile of the targeted end-users, the device type it will be served from, the context of the application (inside a hospital) and the interaction modes (touchscreen vs traditional mouse and keyboard), etc.
2 Design Methodologies and Results
Designing user interfaces for interactive systems in general is a complex process that has to take into consideration many parameters, such as the scope of the end application, its target audience, the functional and non-functional requirements, and the interaction mode (keyboard and mouse, touch, voice, gestures, etc.). In this paper we argue that traditional design guidelines and standards are not adequate, and thus, we focused our work on expanding existing lists with new guidelines to cover emerging interaction requirements for biometric authentication. Similarly, even though we have evidence for the creation of heuristics – for user interface design – in many different domains (robotics, virtual worlds, multimodal mobile applications, Smartphones, etc.), it seems that none of these is biometric related. Quiñones and Rusu [12] presented an extensive literature review conducted from 2006 till 2016 and identified 68 such domains, but none is related to biometric authentication – as described in SpeechXRays project. Even though recent research has shown that usability and reliability play an even more important role than privacy and trust in user acceptance of biometric authentication systems [7] and perceived convenience can be a bigger driver than any increase in security [8], a quick literature review will reveal that the majority of studies in this field concentrate mostly on the technical aspects of various biometric modalities [4, 5] conducting evaluations on their accuracy, reliability and overall performance, such as in the studies presented in [1,2,3, 9, 10]. As of today, at least to our knowledge, there are no concrete user interface guidelines for biometric authentication systems.
2.1 User Interface Design Methodology
The design of the user interfaces of the SPEECHXRAYS system was based on traditional HCI heuristics applied in the context of biometrics authentication. More specifically, Jacob Nielsen’s list of usability heuristics [14] was used as the basis for the application’s interface design (Table 1). Nielsen is an internationally known and well-respected usability engineer who along with Rolf Molich in 1990 developed a list of ten design principles for interactive applications [15].
The list was later refined by Nielsen to what is now commonly known as usability heuristics and the evaluation of any interface against these rules is known as heuristics evaluation. This list of guidelines was chosen because it has been validated through many studies over the years in the field of HCI and it has been proven as an effective method for safeguarding usability. In addition, a literature review on biometric authentication systems was performed to gather any design guidelines or principles specific to biometrics applications as they may have been published in recent empirical studies in this field. Lastly, since one of the main requirements of this biometrics, application was for the system to be device independent, common mobile specific design guidelines and principles were used. Table 2 presents with the list of the collected design guidelines that were used for the UI design, along with the suggested design techniques that were used to fulfill them. Finally, Fig. 2 showcases a sample of the user interface prototype along with the respective design guidelines applied.
2.2 Mobile Application Design Guidelines
There are many sources for mobile application design guidelines, such as articles published by professionals and commercial companies on technology websites and blogs, as well as papers published on scientific magazines and journals. Mobile industry leaders, Apple and Google, have both provided extensive design guidelines to developers of mobile applications for each platform respectively. Many of the published mobile best practices lists are based on Nielsen’s traditional heuristics and have been expanded to include guidelines specific to the mobile use context. For the purpose of this project, a selection of four guidelines were extracted from publications [16,17,18, 20, 21] and used in the design of the user interfaces prototypes. These four were selected because they are complementary to the Nielsen’s heuristics.
G1: Focused Content with One Clear Task.
Designing with minimalism in mind is even more essential for mobiles than desktop application because in mobile devices the users have to deal with smaller screens and touch interaction. Clutter and competing graphical and interaction elements do not enhance user experience and they should be kept to a minimum. Each page should have one central focus and that should be dedicated to the task at hand [17]. The application should guide the users seamlessly through task completion without disrupting their flow. In the biometrics application context, this applies both for the verification and the enrolment processes which include multiple steps.
G2: Provide a Clear Navigational Path.
Again the limitations in the viewing space on mobiles calls for less elaborate menus and navigation mechanisms than those often found in desktop websites. Thus, multi-level menus with sub menus that show on hover and side navigation bars are not recommended in mobile design. In addition, the navigable path to task completion should be clear so that the users will be able to understand right away how they can interact with the application to achieve task completion [17].
G3: Develop a Single Underlying System that Allows for a Unified Experience Across Platforms and Device Sizes.
This guideline is extremely important for all mobile applications and is referred in many studies [16, 17] and especially important for this biometrics authentication system since it addresses one of the main user requirements for the system which is, to be device independent. One of Google’s guidelines is to optimize the entire site for mobile use. Participants in their study had a much easier time navigating mobile-optimized sites than trying to navigate desktop sites on mobile devices. Sites that included a mix of desktop and mobile-optimized pages were actually harder for participants to use than all-desktop sites. Thus it is suggested to design the entire site for mobile use.
G4: Design for Touch.
Designing for touch requires extra care to account for fingers of all shapes and sizes applying varying kinds of pressure to touch screens that respond differently. All form controls, action buttons, and other interaction elements must measure at least 44 points by 44 points and have adequate space around them, so that they can be accurately tapped with a finger [20, 21].
3 Conclusion and Future Work
Despite the rising issues for the security of the biometric data, biometric technology is used for a number of different types of applications ranging from modest (time and attendance of personnel for a small industry) up to expansive (integrity of a whole population cohort such as voters database). Depending on the applications, the benefits of deploying biometric tools may lead to increased security, increased convenience and increased accountability compared to other authentication methods (PINs, passwords etc.). Prior to opting for a biometric system, one must also consider the existing security solutions and requirement in the specific application domain where the biometric system will be embedded. This is critical especially when dealing with services that would allow access to sensitive medical data. The UI described here along with the presented list of design guidelines, will be evaluated to study insights on how to optimally design a modular biometric platform able to be used in the eHealth domain [25]. Users (i.e. Medical specialists) will use the remote biometrics tool of SpeechXRays to access a collaboration platform containing patient’s eHealth record and the data for management of patient’s chronic conditions. The pilot study will also test the context-dependent feature that allows administrators to modify the false accepting rate or false rejection rate trade-off in order to reduce the risk of false reject for low security data and reduce the risk of false accept for high security data.
References
Trewin, S., Swart, C., Koved, L., Martino, J., Singh, K., Ben-David, S.: Biometric authentication on a mobile device: a study of user effort, error and task disruption. In: Proceedings of the 28th Annual Computer Security Applications Conference, pp. 159–168. ACM, December 2012
Nandakumar, K., Jain, A.K.: Biometric template protection: bridging the performance gap between theory and practice. IEEE Sig. Process. Mag. 32(5), 88–100 (2015)
Chingovska, I., Dos Anjos, A.R., Marcel, S.: Biometrics evaluation under spoofing attacks. IEEE Trans. Inf. Forensics Secur. 9(12), 2264–2276 (2014)
Toledano, D.T., Pozo, R.F., Trapote, Á.H., Gómez, L.H.: Usability evaluation of multi-modal biometric verification systems. Interact. Comput. 18(5), 1101–1122 (2006)
Bhagavatula, C., Ur, B., Iacovino, K., Kywe, S.M., Cranor, L.F., Savvides, M.: Biometric authentication on iphone and android: usability, perceptions, and influences on adoption. In: Proceedings of USEC, pp. 1–2 (2015)
Miltgen, C.L., Popovič, A., Oliveira, T.: Determinants of end-user acceptance of biometrics: integrating the “Big 3” of technology acceptance with privacy context. Decis. Support Syst. 56, 103–114 (2013)
De Luca, A., Hang, A., Von Zezschwitz, E., Hussmann, H.: I feel like I’m taking selfies all day! Towards understanding biometric authentication on smartphones. In: Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems, pp. 1411–1414. ACM, April 2015
Patrick, A.S.: Usability and acceptability of biometric security systems. In: Financial Cryptography, p. 105, January 2004
De Luca, A., Hang, A., Brudy, F., Lindner, C., Hussmann, H.: Touch me once and I know it’s you! Implicit authentication based on touch screen patterns. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 987–996. ACM, May 2012
Blanco-Gonzalo, R., Diaz-Fernandez, L., Miguel-Hurtado, O., Sanchez-Reillo, R.: Usability evaluation of biometrics in mobile environments. In: 2013 6th International Conference on Human System Interaction (HSI), pp. 123–128. IEEE, June 2013
Jain, A.K., Nandakumar, K., Ross, A.: 50 years of biometric research: accomplishments, challenges, and opportunities. Pattern Recogn. Lett. 79, 80–105 (2016)
Quiñones, D., Rusu, C.: How to develop usability heuristics: a systematic literature review. Comput. Stand. Interfaces 53, 89–122 (2017)
Jain, A., Ross, A.A., Nandakumar, K.: Introduction to Biometrics. Springer Science & Business Media, Berlin (2011)
Nielsen, J.: Usability inspection methods. In: Conference Companion on Human Factors in Computing Systems, pp. 413–414. ACM, April 1994
Molich, R., Nielsen, J.: Improving a human-computer dialogue. Commun. ACM 33(3), 338–348 (1990)
Yáñez Gómez, R., Cascado Caballero, D., Sevillano, J.L.: Heuristic evaluation on mobile interfaces: a new checklist. Sci. World J. 2014 (2014)
Joyce, G., Lilley, M.: Towards the development of usability heuristics for native smartphone mobile applications. In: Marcus, A. (ed.) DUXU 2014. LNCS, vol. 8517, pp. 465–474. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-07668-3_45
Vilar Neto, E., Campos, F.F.: Evaluating the usability on multimodal interfaces: a case study on tablets applications. In: Marcus, A. (ed.) DUXU 2014. LNCS, vol. 8517, pp. 484–495. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-07668-3_47
Unar, J.A., Seng, W.C., Abbasi, A.: A review of biometric technology along with trends and prospects. Pattern Recogn. 47(8), 2673–2688 (2014)
Apple Developer: UI design do’s and don’ts (2017). https://developer.apple.com/design/tips/
Google Developers: Up and running with material design (2017). https://developer.android.com/design/index.html
Spanakis, E.G., Spanakis, M., Karantanas, A., Marias, K.: Secure access to patient’s health records using SpeechXRays a multi-channel biometrics platform for user authentication. In: 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Orlando, FL, USA, 16–20 August 2016 (2016)
Chronaki, C., et al.: An eHealth platform for instant interaction among health professionals. In: Computers in Cardiology 2003, Thessaloniki Chalkidiki, 21–24 September 2003, vol. 30, pp. 101–104 (2003). (02766574)
Spat, S., et al.: A mobile android-based application for in-hospital glucose management in compliance with the medical device directive for software. In: 2nd International ICST Conference on Wireless Mobile Communication and Healthcare (MobiHealth 2011), Kos Island, Greece, 5–7 October 2011 (2011)
Spanakis, E.G., et al.: Technology-based innovations to foster personalized healthy lifestyles and well-being: a targeted review. J. Med. Internet Res. 18(6), e128 (2016). https://doi.org/10.2196/jmir.4863
Acknowledgement
This work is supported by the research project “SpeechXRays” which receives funding from the European Commission (EC) through Horizon 2020 Grant agreement No. 653586.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Adami, I., Antona, M., Spanakis, E.G. (2018). Multi-modal User Interface Design for a Face and Voice Recognition Biometric Authentication System. In: Perego, P., Rahmani, A., TaheriNejad, N. (eds) Wireless Mobile Communication and Healthcare. MobiHealth 2017. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 247. Springer, Cham. https://doi.org/10.1007/978-3-319-98551-0_20
Download citation
DOI: https://doi.org/10.1007/978-3-319-98551-0_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-98550-3
Online ISBN: 978-3-319-98551-0
eBook Packages: Computer ScienceComputer Science (R0)