Donald E. Maurer

Benchmarking Quality-Dependent and Cost-Sensitive Score-Level Multimodal Biometric Fusion Algorithms

Automatically verifying the identity of a person by means of biometrics (e.g., face and fingerprint) is an important application in our day-to-day activities such as accessing banking services and security control in airports. To increase the system reliability, several biometric devices are often used. Such a combined system is known as a multimodal biometric system. This paper reports a benchmarking study carried out within the framework of the BioSecure DS2 (Access Control) evaluation campaign organized by the University of Surrey, involving face, fingerprint, and iris biometrics for person authentication, targeting the application of physical access control in a medium-size establishment with some 500 persons. While multimodal biometrics is a well-investigated subject in the literature, there exists no benchmark for a fusion algorithm comparison. Working towards this goal, we designed two sets of experiments: quality-dependent and cost-sensitive evaluation. The quality-dependent evaluation aims at assessing how well fusion algorithms can perform under changing quality of raw biometric images principally due to change of devices. The cost-sensitive evaluation, on the other hand, investigates how well a fusion algorithm can perform given restricted computation and in the presence of software and hardware failures, resulting in errors such as failure-to-acquire and failure-to-match. Since multiple capturing devices are available, a fusion algorithm should be able to handle this nonideal but nevertheless realistic scenario. In both evaluations, each fusion algorithm is provided with scores from each biometric comparison subsystem as well as the quality measures of both the template and the query data. The response to the call of the evaluation campaign proved very encouraging, with the submission of 22 fusion systems. To the best of our knowledge, this campaign is the first attempt to benchmark quality-based multimodal fusion algorithms. In the presence of changing image quality which may be due to a change of acquisition devices and/or device capturing configurations, we observe that the top performing fusion algorithms are those that exploit automatically derived quality measurements. Our evaluation also suggests that while using all the available biometric sensors can definitely increase the fusion performance, this comes at the expense of increased cost in terms of acquisition time, computation time, the physical cost of hardware, and its maintenance cost. As demonstrated in our experiments, a promising solution which minimizes the composite cost is sequential fusion, where a fusion algorithm sequentially uses match scores until a desired confidence is reached, or until all the match scores are exhausted, before outputting the final combined score.

Information handover for track-to-track correlation

Abstract The ability of an intercepting missile to select a high-value target in a ballistic missile threat complex would be enhanced if offboard radar tracks on the threat are transmitted to the intercepting missile and combined with the onboard infrared (IR) track picture. Correct track-to-track correlation, however, is a prerequisite to successful information fusion. This paper attempts to quantify the effect on the probability of correctly correlating two independently developed track sets of various types of information that might be included in the handover data set. Theoretical results are obtained that suggest modifications to current correlation algorithms to reduce information handover to the missile and increase computational speed. Several information handover options are compared to illustrate the use of this methodology to determine tradeoffs between the type and quality of information required to enhance target selection and the bandwidth, computational, and time constraints imposed by currently operational systems. These analyses also provide a basis for assessing the capability of current systems to support handover and for setting design requirements for proposed systems.

Conceptual design and algorithm evaluation for a very accurate imaging star tracker for deep- space optical communications

The National Aeronautics and Space Administration is planning high data rate optical communications for future deep space missions. The Johns Hopkins University Applied Physics Laboratory (JHU/APL) is responding by developing concepts for implementing optical communications terminals that are more compact and lightweight than heretofore. An essential requirement for these long-range optical links is a high-precision pointing and tracking system. Focal plane array (FPA)-based star trackers that enable open-loop pointing and tracking are necessary. Spacecraft attitude instabilities, emphemeris errors, tracking sensor noise, clock errors, and mechanical misalignments are among the error sources that must be minimized and compensated for. To achieve this JHU/APL has developed an imaging star tracker concept using redundant multi-aperture FPAs symmetrically disposed about the laser downlink. Centroid estimation and pattern matching techniques account for aberration and motion errors. Robustness, sensitivity to detection thresholds, field-of-view sizing, number of stars per frame, missed detections, false alarms, and position biases, as well as stellar catalog size and star selection, will be described. Finally the conceptual design of a frame-to-frame integration method and sensor fusion algorithm (such as a Kalman filter) will be considered. The goal is to achieve a system pointing and tracking error significantly less than 1 μrad.

Merlin microbolometer camera calibration

The Low Cost Gun Launched Seeker is a component of the Navys effort to develop effective weapons for surface fire support missions by enhancing the performance of projectiles like the Extended Range Guided Munitions with low-cost, uncooled infrared (IR) staring focal plane array terminal seekers. IR target images for validating target detection algorithms were collected using a Merlin long wave camera from Indigo Systems. This paper characterizes the camera in order to develop performance parameters for simulating the seeker and to understand features in the imagery. These parameters include temperature response, temporal noise characteristics, fixed pattern noise, and the modulation transfer function.