Search

Your search keyword '"Haraksim, Rudolf"' showing total 33 results
Start Over Author "Haraksim, Rudolf"
33 results on '"Haraksim, Rudolf"'

1. FaceQnet: Quality Assessment for Face Recognition based on Deep Learning

Author

Hernandez-Ortega, Javier, Galbally, Javier, Fierrez, Julian, Haraksim, Rudolf, and Beslay, Laurent

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

In this paper we develop a Quality Assessment approach for face recognition based on deep learning. The method consists of a Convolutional Neural Network, FaceQnet, that is used to predict the suitability of a specific input image for face recognition purposes. The training of FaceQnet is done using the VGGFace2 database. We employ the BioLab-ICAO framework for labeling the VGGFace2 images with quality information related to their ICAO compliance level. The groundtruth quality labels are obtained using FaceNet to generate comparison scores. We employ the groundtruth data to fine-tune a ResNet-based CNN, making it capable of returning a numerical quality measure for each input image. Finally, we verify if the FaceQnet scores are suitable to predict the expected performance when employing a specific image for face recognition with a COTS face recognition system. Several conclusions can be drawn from this work, most notably: 1) we managed to employ an existing ICAO compliance framework and a pretrained CNN to automatically label data with quality information, 2) we trained FaceQnet for quality estimation by fine-tuning a pre-trained face recognition network (ResNet-50), and 3) we have shown that the predictions from FaceQnet are highly correlated with the face recognition accuracy of a state-of-the-art commercial system not used during development. FaceQnet is publicly available in GitHub., Comment: Preprint version of a paper accepted at ICB 2019

Published
2019

13. Study on Face Identification Technology for its implementation in the Schengen Information System

Author

GALBALLY HERRERO JAVIER, FERRARA PASQUALE, HARAKSIM RUDOLF, PSYLLOS APOSTOLOS, and BESLAY LAURENT

Abstract

The present report assesses the readiness and availability of automatic face recognition technology for its integration in the Schengen Information System (SIS). This functionality has been introduced in the latest SIS Regulation adopted on the 28th of November 2018. The legislation determines the use of this technology first in the context of regular border crossing, however it also foresees its possible use in the near future in the context of police and judicial cooperation. The first part of the report introduces automatic face recognition technology, presenting a thorough review of the state of the art, which concludes with the lessons learnt and the challenges faced by automatic face recognition systems. The second part makes an analysis of how face recognition technology can be integrated within CS-SIS and presents the different use-cases in which the functionality will be exploited. A number of recommendations for the successful implementation of face processing techniques in CS-SIS are then proposed., JRC.E.3-Cyber and Digital Citizens' Security

Published
2019

14. Study on Fingermark and Palmmark Identification Technologies for its Implementation in the Schengen Information System

Author

HARAKSIM RUDOLF, GALBALLY HERRERO JAVIER, and BESLAY LAURENT

Abstract

The report assesses the technology readiness and availability of new functionalities – based on automatic fingermark and palmmark recognition technologies – for their integration into the Schengen Information System (SIS). These functionalities have been introduced in the revised SIS Regulations adopted on 28th of November 2018, both in the context of police and judicial cooperation. The report is structured in two parts. In Part I, the automatic fingermark and palmmark recognition functionalities are introduced together with a review of the latest developments and state of the art, quality metrics and important biometric standards are provided; and it is concluded with a summary section entitled “lessons learnt”. In Part II, the functionalities are placed into the context of Schengen Information System. Use-cases for border control and police and judiciary cooperation in criminal matters are presented, and a list of recommendations for the successful implementation of fingermark and palmmark processing technologies into the Schengen Information System are provided., JRC.E.3-Cyber and Digital Citizens' Security

Published
2019

15. Automatic fingerprint recognition: from children to elderly Ageing and age effects

Author

BESLAY LAURENT, GALBALLY HERRERO JAVIER, and HARAKSIM RUDOLF

Abstract

By courtesy of the Portuguese Government, DG JRC has received a comprehensive set of fingerprint data from individuals aged 0-25 and 65-98. The main purpose of the proposed experiments is to deepen the understanding regarding the physiological development of the fingertip ridge structure over time and its impact on automated fingerprint recognition. The experiments explore three biometric processes in the light of age, ageing and growth effects. These effects are demonstrated and validated. A growth model is also developed and validated. The report concludes with a series of recommendations for enhanced implementation of automated fingerprint recognition system and suggestions for further researches., JRC.E.3-Cyber and Digital Citizens' Security

Published
2018

26. Validation of Likelihood Ratio Methods Used for Forensic Evidence Evaluation: Application in Forensic Fingerprints

Author

Haraksim, Rudolf, Meuwly, Didier, and Veldhuis, Raymond N.J.

Subjects
EC Grant Agreement nr.: FP7-PEOPLE-ITN-2008, Ratio Methods, SCS-Safety, Validation, Fingerprints, EWI-25056, METIS-305078, IR-91812, Forensic Evidence Evaluation
Abstract

In this chapter the Likelihood Ratio (LR) inference model will be introduced, the theoretical aspects of probabilities will be discussed and the validation framework for LR methods used for forensic evidence evaluation will be presented. Prior to introducing the validation framework, following questions will be addressed: “which aspects of a forensic evaluation scenario need to be validated?‿, “what is the role of the LR as part of a decision process?‿ and “how to deal with uncertainty in the LR calculation?‿ The answers to these questions are necessary to define the validation strategy based on the validation criteria. The questions: “what to validate?‿ focusing on defining validation criteria and methods, and “how to validate?‿ dealing with the implementation of a validation protocol, form the core of this chapter. The validation framework described can be used to provide assistance to the forensic practitioners, when determining the suitability and applicability of the LR method developed in the forensic practice by introducing performance characteristics, performance metrics, validation criteria and the decision thresholds. This chapter will start with the introduction of the LR inference model, followed by the validation framework proposed.

Published
2014

28. Validation of likelihood ratio methods for forensic evidence evaluation handling multimodal score distributions.

Author

Haraksim, Rudolf, Ramos, Daniel, and Meuwly, Didier

Subjects
*LIKELIHOOD ratio tests, *FORENSIC sciences, *HUMAN fingerprints, *BIOMETRIC identification, *ROBUST control
Abstract

This study presents a method for computing likelihood ratios (LRs) from multimodal score distributions, as the ones produced by some commercial off-the-shelf automated fingerprint identification systems (AFISs). The AFIS algorithms used to compare fingermarks and fingerprints were primarily developed for forensic investigation rather than for forensic evaluation purposes. Thus, in some of those algorithms, the computation of discriminating scores is speed-optimised. In the case of the AFIS algorithm used in this work, the speed-optimisation is achieved by performing the comparison in three different stages, each of which outputs scores of different magnitudes. As a consequence, all scores together present a multimodal distribution, even though each fingermark-to-fingerprint comparison generates one single score. This multimodal distribution of scores might be typical for other biometric systems or other algorithms, and the method proposed in this work can be also applied to those cases. As a result, the authors propose a probabilistic model for LR computation that presents more robustness to overfitting and data sparsity than other traditional approaches, like the use of models based on kernel density functions. [ABSTRACT FROM AUTHOR]

Published
2017
Full Text
View/download PDF

33. Likelihood ratio data to report the validation of a forensic fingerprint evaluation method.

Author

Ramos D, Haraksim R, and Meuwly D

Abstract

Data to which the authors refer to throughout this article are likelihood ratios (LR) computed from the comparison of 5-12 minutiae fingermarks with fingerprints. These LRs data are used for the validation of a likelihood ratio (LR) method in forensic evidence evaluation. These data present a necessary asset for conducting validation experiments when validating LR methods used in forensic evidence evaluation and set up validation reports. These data can be also used as a baseline for comparing the fingermark evidence in the same minutiae configuration as presented in (D. Meuwly, D. Ramos, R. Haraksim,) [1], although the reader should keep in mind that different feature extraction algorithms and different AFIS systems used may produce different LRs values. Moreover, these data may serve as a reproducibility exercise, in order to train the generation of validation reports of forensic methods, according to [1]. Alongside the data, a justification and motivation for the use of methods is given. These methods calculate LRs from the fingerprint/mark data and are subject to a validation procedure. The choice of using real forensic fingerprint in the validation and simulated data in the development is described and justified. Validation criteria are set for the purpose of validation of the LR methods, which are used to calculate the LR values from the data and the validation report. For privacy and data protection reasons, the original fingerprint/mark images cannot be shared. But these images do not constitute the core data for the validation, contrarily to the LRs that are shared.

Published
2016
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results