P329 - BIOSIG 2022 - Proceedings of the 21st International Conference of the Biometrics Special Interest Group
Auflistung nach:
Auflistung P329 - BIOSIG 2022 - Proceedings of the 21st International Conference of the Biometrics Special Interest Group nach Erscheinungsdatum
1 - 10 von 35
Treffer pro Seite
Sortieroptionen
- KonferenzbeitragEvaluating Face Image Quality Score Fusion for Modern Deep Learning Models(BIOSIG 2022, 2022) Schlett, Torsten; Rathgeb, Christian; Tapia, Juan E.; Busch, ChristophFace image quality assessment algorithms attempt to estimate the utility of face images for biometric systems, typically face recognition, since the performance of these systems can be limited by the image quality. Hand-crafted quality score fusion has previously been examined for a variety of mostly factor-specific quality assessment algorithms. This paper instead examines score fusion for various recent “monolithic” quality assessment deep learning models. The evaluation methodology is based on Error-versus-Reject-Characteristic partial-Area-Under-Curve values, which are used to quantitatively rank quality assessment configurations in a face recognition context. Mean quality score fusion configurations were found to slightly improve performance on the TinyFace database, while the tested fusion types were ineffective on the LFW database.
- KonferenzbeitragWorst-Case Morphs: a Theoretical and a Practical Approach(BIOSIG 2022, 2022) Una Kelly, Luuk Spreeuwers and Raymond VeldhuisFace Recognition (FR) systems have been shown to be vulnerable to morphing attacks. We examine exactly how challenging morphs can become. By showing a worst-case construction in the embedding space of an FR system and using a mapping from embedding space back to image space we generate images that show that this theoretical upper bound can be approximated if the FR system is known. The resulting morphs can also succesfully fool unseen FR systems and are useful for exploring and understanding the weaknesses of FR systems. Our method contributes to gaining more insight into the vulnerability of FR systems.
- KonferenzbeitragProcessing Information Extracted from the Human Body: Measurements of Biological and Behavioural Signals as a Unifying Link(BIOSIG 2022, 2022) Lydia BelkadiThis contribution proposes the concept of “measurements of biological and behavioural signals” for interdisciplinary research on the automated processing of information from the human body. This concept has merits in mitigating legal definitions’ instability. We further aim to bridge legal and technical vocabularies, both responding to specific methodologies. Revising this concept should enable a more coherent approach and account for information about the human body, emerging sensing devices, and automated systems.
- KonferenzbeitragVerification Failures: Assessing the Sample Quality of Fingerprints collected in an African Election Setting(BIOSIG 2022, 2022) Oluwafemi Samuel, Iain Martin and Ludovic MagerandThe use of biometric technology has become an integral part of elections in Africa, the primary aim being delivery of credible elections. Fingerprint verification of eligible voters is central to this development. Deployment of fingerprint verification technology at elections has not been without its challenges for African countries. Failed verification incidents have been recorded in countries like Ghana, Kenya and Nigeria. A case is made on the need to identify the causes of these incidents before any reasonable solution can be proposed. This research investigates some of the possible causes by analysing the quality of sample fingerprints from a new dataset of an African population collected in election settings. NIST’s NFIQ 2.2 was used for the fingerprint quality assessment with initial analyses reported in this work.
- KonferenzbeitragDeDiM: De-identification using a diffusion model(BIOSIG 2022, 2022) Hidetsugu Uchida, Narishige Abe and Shigefumi YamadaAs a countermeasure against malicious authentication in a face recognition system using a face image obtained from SNS or the like, de-identification methods based on adversarial example have been studied. However, since adversarial example directly uses the gradient information of a face recognition model, it is highly dependent on the model, and a de-identification effect and image quality are difficult to achieve for an unknown recognition model. In this study, we propose a novel de-identification method based on a diffusion model, which has high generalizability to an unknown recognition model by applying minute changes to face shapes. Experiments using LFW showed that the proposed method has a higher de-identification effect for unknown models and better image quality than a conventional method using adversarial example.
- KonferenzbeitragFundamental Study of Neonate Fingerprint Recognition Using Fingerprint Classification(BIOSIG 2022, 2022) Yoshinori Koda, Haruki ImaiUNICEF reported that many of the 2.4 million deaths within 28 days of birth were preventable with appropriate vaccination. There are several reasons why babies cannot be vaccinated, for example, the medical staff does not have appropriate vaccination history management to control who and when they should be vaccinated. To properly manage vaccination history and promote its widespread use, personal identification after birth is essential, and a neonate fingerprint identification technology could be one of the solutions. In this paper, we develop a fingerprint scanner with a 2,674ppi high-resolution CMOS sensor specifically designed to acquire neonatal fingerprints by integrating positive comments from users in the research field on the previous prototype. We also propose a neonate fingerprint identification method based on fingerprint classification.
- KonferenzbeitragCan point-cloud based neural networks learn fingerprint variability?(BIOSIG 2022, 2022) Dominik Söllinger, Robert JöchlSubject- and environmental-specific variations affect the fingerprint recognition process. Quality metrics are capable of detecting and rating severe degradations. However, measuring natural variability, occurring during different fingerprint acquisitions, is not in the scope of these metrics. This work proposes the use of genuine comparison scores as a measure of variability. It is shown that the publicly available PLUS-MSL-FP dataset exhibits large natural variations which can be used to distinguish between different acquisition sessions. Furthermore, it is showcased that point-cloud (set) based neural networks are promising candidates for processing fingerprint imagery as they provide precise control over the input parameters. Experiments show that point-cloud based neural networks are capable of distinguishing between the different sessions in the PLUS-MSL-FP dataset solely based on FP minutiae locations.
- KonferenzbeitragGAIT3: An Event-based, RGB and Thermal Gait Database(BIOSIG 2022, 2022) Mohamed Eddine and Jean-Luc DugelayIdentifying people by their gait has gained popularity in the last twenty years. Recent gait recognition methods use acquisitions extracted from advanced sensors such as cameras, depth sensors, microphones, etc. Recently, event-based cameras, a new family of cameras, are gaining popularity. They are vision sensors that differ completely from conventional cameras: instead of capturing images at a fixed rate, they asynchronously measure per-pixel brightness changes generated by moving objects. This motivated us to use it for individual recognition by gait. In this paper, we provide means for multimodal gait recognition, by introducing the “Event-based, RGB, and Thermal Gait” database. This database is the first that contains event-camera acquisition, simultaneously with conventional RGB and thermal videos. It contains recordings of people in three variations: normal walking, quick walking, and walking with a backpack. We also present experiments using a baseline algorithm based on gait energy images adapted to event-based camera output. Then we present a comparative experiment against RGB and thermal videos, using the same algorithm, that shows an advantage for event-based data.
- KonferenzbeitragAn anomaly detection approach for backdoored neural networks: face recognition as a case study(BIOSIG 2022, 2022) Alexander Unnervik and Sébastien MarcelBackdoor attacks allow an attacker to embed functionality jeopardizing proper behavior of any algorithm, machine learning or not. This hidden functionality can remain inactive for normal use of the algorithm until activated by the attacker. Given how stealthy backdoor attacks are, consequences of these backdoors could be disastrous if such networks were to be deployed for applications as critical as border or access control. In this paper, we propose a novel backdoored network detection method based on the principle of anomaly detection, involving access to the clean part of the training data and the trained network.We highlight its promising potential when considering various triggers, locations and identity pairs, without the need to make any assumptions on the nature of the backdoor and its setup. We test our method on a novel dataset of backdoored networks and report detectability results with perfect scores.
- KonferenzbeitragCase study of the acquisition of contactless fingerprints in a real police setting(BIOSIG 2022, 2022) Axel Weissenfeld, Reinhard SchmidBiometric recognition systems integrated into mobile devices have gained acceptance during recent years. Developments in fingerprint acquisition technology have resulted in touchless mobile devices that acquire high quality fingerprints. While authorities are particular interested on mobile solutions, they have databases containing fingerprint data mainly acquired using contactbased devices. Therefore, they are interested in the accuracy of cross-sensor fingerprint recognition. We present a case study of a comprehensive matching comparison on real fingerprint data acquired by national police officers. The objective of this study is: (i) to analyse the feasibility when comparing data acquired using a typical contact-based fingerprint device against data acquired using a new contactless device, and (ii) the feedback of the end user (i.e. national police officers) regarding the acquisition process. Obtained results are promising and the current prototype shows its feasibility for operational police use. The end users expressed their satisfaction with the developed prototype and they suggested extra functionalities towards a practical solution for police officers.