Human-Biometric Sensor Interaction

Voice and face interaction evaluation of a mobile authentication platform

“…The HBSI framework [3], devised by Purdue University, provides a set of interaction metrics to reach a thorough understanding of how users interact with biometric system and its impact on the biometric performance. The HBSI model is formed of three elements: human (the participants of this experiment), sensor (either the front camera or the microphone of the smartphone) and biometric system (the PIDaaS platform).…”

Interaction evaluation of a mobile voice authentication system

“…In order to perform such as analysis, the HBSI framework [2] devised at the Purdue University has been applied. The HBSI framework proposes interaction metrics to reach a deeper understanding of commonly used biometric performance metrics such as Failure to Enrol (FTE) or Failure to Acquire (FTA) [3].…”

“…The HBSI presentation metrics are defined by the type of presentations the users make, and their categorisation depends on whether the user makes a correct or incorrect presentation, whether the presentation was detected by the biometric system and whether the presentation was correctly classified by the biometric system [2]. Taking into account these three factors the presentations are classified as unsuccessful interactions: Defective Interaction (DI), Failure to Detect (FTD), Concealed Interaction (CI), Failure to Process (FTP), False Interaction (FI); or as a successful interaction: Successfully Processed Sample (SPS) (see Figure 2).…”

“…DI or the FTD presentations). Furthermore, the HBSI framework also defines a set of metrics taken from the usability and the biometric system performance disciplines in order to obtain a holistic view of the user's interaction with the biometric implementation, Figure 3: Figure 3 The HBSI evaluation metrics [9] Figure 1 The HBSI model [2] In this work, we propose an integration methodology for the evaluation of mobile biometrics systems interaction, by using mobile analytical tools and biometric system logs to ensure the sufficient information to enable and facilitate the HBSI analysis. Mobile analytical tools, such as Flurry Analytics [10], are commonly used for mobile applications development providing a deep understanding of the user-application interaction: how users navigate the different options, what events they are conducting.…”

“…In order to ensure the usability and effective interaction with the final PIDaaS Mobile Application (PMA), the Human-Biometric-Sensor Interaction (HBSI) framework for biometric evaluations [2] has been applied to the initial version.…”