Eric P. Kukula

The Human–Biometric-Sensor Interaction Evaluation Method: Biometric Performance and Usability Measurements

This paper discusses the human-biometric-sensor interaction (HBSI) evaluation method that uses ergonomics, usability, and sample quality criteria as explanatory variables for the overall biometric system performance. The HBSI method was proposed because of questions regarding the thoroughness of traditional system-level performance evaluation metrics such as the failure-to-acquire (FTA) rate, the failure-to-enroll (FTE) rate, the false-accept rate (FAR), and the false-reject rate (FRR). Data were collected from 85 individuals over three visits that accounted for 25 867 user interactions with three swipe-based fingerprint sensors. The results in this paper revealed that traditional biometric evaluations that focus on system-level metrics are not providing sufficient reporting details regarding the user interaction with the devices. In this paper, the systemic FTA rate of 14.38% was shown to be segmented into three metrics: false interaction (FI), failure to detect (FTD), and concealed interaction (CI). The results show that the FI accounted for 69.05% of the systemic FTA presentations, FTD accounted for 30.71%, and CI accounted for 0.24%. Overall, the HBSI evaluation method and framework for biometric interactions provided new metrics that improve the analysis capabilities for biometric performance evaluations as it links system feedback to the human-sensor interaction, enabling researchers, system designers, and implementers to understand if the issues are the result of the system, the user, both the system and the user, or some other extraneous factor.

The effects of human interaction on biometric system performance

This paper discusses the impact of human interaction with biometric devices and its relationship to biometric performance. The authors propose a model outlining the Human-Biometric Sensor Interaction and discuss its necessity through case studies in fingerprint recognition, hand geometry, and dynamic signature verification to further understand the human-sensor interaction issues and underlying problems that they present to the biometric system. Human factors, human-computer interaction and digital human modeling are considered in the context of current and future biometric research and development.

Effects of illumination changes on the performance of Geometrix FaceVision/spl reg/ 3D FRS

This evaluation examined the effects of four frontal light intensities on the performance of a 3D face recognition algorithm, specifically testing the significance between an unchanging enrollment illumination condition (220-225 lux) and four different illumination levels for verification. The evaluation also analyzed the significance of external artifacts (i.e. glasses) and personal characteristics (i.e. facial hair) on the performance of the face recognition system (FRS). Collected variables from the volunteer crew included age, gender, ethnicity, facial characteristics, hair covering the forehead, scars on the face, and glasses. The analysis of data revealed that there are no statistically significant differences between environmental lighting and 3D FRS performance when a uniform or constant enrollment illumination level is used.

Human-Biometric Sensor Interaction: Impact of Training on Biometric System and User Performance

Increasingly sophisticated biometric methods are being used for a variety of applications in which accurate authentication of people is necessary. Because all biometric methods require humans to interact with a device of some type, effective implementation requires consideration of human factors issues. One such issue is the training needed to use a particular device appropriately. In this paper, we review human factors issues in general that are associated with biometric devices and focus more specifically on the role of training.

Implementing Ergonomic Principles in a Biometric System: A Look at the Human Biometric Sensor Interaction (HBSI)

This paper discusses the implementation of ergonomic principles in a biometric system. Historically, the biometrics community has performed limited work in the area of ergonomics and usability. This research discusses an experiment involving a swipe fingerprint sensor which examined the human interaction with the biometric device called the human biometric sensor interaction (HBSI). The purpose of this study was to examine issues related to fingerprint acquisition of all ten digits. The results revealed that there are fingerprints that have higher failure to acquire (FTA) rates than others, indicating others factors apart from image quality, such as how the user interacts with the device may be at play. Thus, more research is needed in the area of biometric usability and ergonomics, namely understanding how the human interacts with the biometric sensor

A Definitional Framework for the Human-Biometric Sensor Interaction Model

Existing definitions for biometric testing and evaluation do not fully explain errors in a biometric system. This paper provides a definitional framework for the Human Biometric-Sensor Interaction (HBSI) model. This paper proposes six new definitions based around two classifications of presentations, erroneous and correct. The new terms are: defective interaction (DI), concealed interaction (CI), false interaction (FI), failure to detect (FTD), failure to extract (FTX), and successfully acquired samples (SAS). As with all definitions, the new terms require a modification to the general biometric model developed by Mansfield and Wayman [1].

Evaluation of a facial recognition algorithm across three illumination conditions

This work evaluated the performance of a commercially available face recognition algorithm for the verification of an individuals identity pertaining to three enrollment illumination levels. Existing facial recognition technology from still or video sources is becoming a practical tool for law enforcement, security, and counter-terrorist applications despite the limitations of the current technology. At this time, facial recognition has been implemented in limited applications, but has not been exhaustively studied in adverse conditions, which has initiated continuing study aimed at improving algorithms to compare images or representations of images to recognize a suspect (Paul, 2002). Moreover, this evaluation examined the influence of variations in illumination levels on the performance of a face recognition algorithm, specifically testing the significance between verification attempts and enrollment conditions with respect to factors of age, gender, ethnicity, facial characteristics, and facial obstructions. The results of this evaluation showed that for low and medium illuminance enrollments, there was a statistically significant difference between verification attempts made at low, medium, and high illuminance. However, for the high illuminance enrollment, there was no statistically significant difference between verification attempts made at low, medium, or high illuminance. Furthermore, this evaluation showed that the enrollment illumination level is a better indicator of the verification rate than the verification illumination level.

Securing a restricted site - biometric authentication at entry point

We evaluated the performance of a commercially available facial recognition algorithm for the verification of an individuals identity (1:1) across three illumination levels. Existing facial recognition technology from still or video sources is becoming a practical tool for law enforcement, security, and counter-terrorist applications despite the limitations of current technology. At this time, facial recognition holds promise and has been implemented in limited applications, but has not been exhaustively researched in adverse conditions, which has initiated continuing research aimed at improving algorithms to compare images or representations of images to recognize a suspect [Paul, R. (2002)]. This evaluation examines the influence of variances in illumination levels on the performance of a facial recognition algorithm, specifically with respect to factors of age, gender, ethnicity, facial characteristics, and facial obstructions.

Facial recognition at Purdue University's airport - 2003-2008

Post September 11, 2001, there has been an increased focus by the airline industry and governments to evaluate various technologies associated with security and identification. Automatic identification and data capture (AIDC) technologies have been used extensively in airports and the aviation industry for a number of years prior to September 11, in applications ranging from bar coded baggage tags to magnetic stripes on boarding cards. Although previously used in limited airport applications, there is now a renewed focus on another branch of automatic identification technology, namely biometrics. This paper presents a structured methodology for developing a testing protocol for face recognition at the Student Flight Operations Center at the Purdue University airport which will assess the performance of a commercially available off-the-shelf product over a five year period.