Computation of Likelihood Ratios in Fingerprint Identification for Configurations of Three Minutiæ

Neumann, Cédric; Champod, Christophe; Puch-Solis, Roberto; Egli, Nicole; Anthonioz, Alexandre; Meuwly, Didier; Bromage-Griffiths, Andie

doi:10.1111/j.1556-4029.2006.00266.x

Cited by 80 publications

(60 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The coherence is observed in the Tippett plots when with the increasing number of minutiae there is a decreasing trend in the rates of misleading evidence and an increase in the separation of the curves. The rate of misleading evidence in favor of H d (RMED [24,26]) decreases from 31% for 5-minutiae configurations to 3.5% for 12-minutiae configurations, while the rate of misleading evidence in favor of H p (RMEP [24,26]) decreases from 1.2% for 5-minutiae configurations to 0.06% for 12-minutiae configurations.…”

Section: Resultsmentioning

confidence: 97%

Measuring coherence of computer-assisted likelihood ratio methods

Haraksim

Ramos

Meuwly

et al. 2015

Forensic Science International

Self Cite

View full text Add to dashboard Cite

Measuring the performance of forensic evaluation methods that compute likelihood ratios (LRs) is relevant for both the development and the validation of such methods. A framework of performance characteristics categorized as primary and secondary is introduced in this study to help achieve such development and validation. Groundtruth labelled fingerprint data is used to assess the performance of an example likelihood ratio method in terms of those performance characteristics. Discrimination, calibration, and especially the coherence of this LR method are assessed as a function of the quantity and quality of the trace fingerprint data. Assessment of the coherence revealed a weakness of the comparison algorithm in the computer-assisted likelihood ratio method used. ABSTRACTMeasuring the performance of forensic evaluation methods that compute likelihood ratios (LRs) is relevant for both the development and the validation of such methods. A framework of performance characteristics categorized as primary and secondary is introduced in this study to help achieve such development and validation. Ground-truth labelled fingerprint data is used to assess the performance of an example likelihood ratio method in terms of those performance characteristics. Discrimination, calibration, and especially the coherence of this LR method are assessed as a function of the quantity and quality of the trace fingerprint data.Assessment of the coherence revealed a weakness of the comparison algorithm in the computer-assisted likelihood ratio method used.

show abstract

Section: Resultsmentioning

confidence: 97%

Measuring coherence of computer-assisted likelihood ratio methods

Haraksim

Ramos

Meuwly

et al. 2015

Forensic Science International

Self Cite

View full text Add to dashboard Cite

show abstract

“…One major shortcoming of this study is that the intra-class variation (see Figure 3) was not accounted for since only one image per finger was utilized. Neumann et al [33], [34], [35] developed a fingerprint matching procedure based on matching a local neighborhood of a small number of minutiae and then converting the resulting similarity value s into a likelihood ratio (LR),…”

Section: B Empirical Approachesmentioning

confidence: 99%

“…In [34], a kernel approach was used to estimate the genuine and impostor score densities whereas, in [33], a mixture of Gaussians was used. In [35], a combination of exponential and beta functions of the score values was used to compute the likelihood ratio.…”

Section: B Empirical Approachesmentioning

confidence: 99%

Evidential Value of Automated Latent Fingerprint Comparison: An Empirical Approach

Nagar

Choi

Jain

2012

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

Abstract-Latent fingerprints are routinely recovered from crime scenes and are compared with available databases of known fingerprints for identifying criminals. However, current procedures to compare latent fingerprints to large databases of full (rolled or plain) fingerprints are prone to errors. This suggests caution in making conclusions about a suspect's identity based on a latent fingerprint comparison. A number of attempts have thus been made to measure the utility of a fingerprint comparison in making a correct accept/reject decision or its evidential value. These approaches, however, either do not represent the stateof-the-art in fingerprint matching due to unrealistic modeling assumptions or they lack simple interpretation. We argue that the posterior probability of two fingerprints belonging to different fingers given their match score, referred to as the Non-match probability (NMP), effectively captures any implicating evidence of the comparison. NMP is computed using state-of-the-art matchers and is easy to interpret. To incorporate the effect of image quality, number of minutiae, and size of the latent on NMP value, we compute the NMP vs. match score plots separately for image pairs (latent and full fingerprints) with different characteristics. Given the paucity of latent fingerprint databases in public domain, we simulate latent fingerprints using two full fingerprint databases (NIST SD-14 and Michigan State Police) by cropping regions of three different sizes. We appropriately validate this simulation using four latent databases (NIST SD-27 and three proprietary latent databases) and two state-of-the-art fingerprint matchers to compute their respective match scores. We also describe the way a latent fingerprint examiner would use the proposed framework to compute the evidential value of a latent-full print pair comparison in practice.

show abstract

“…Based on this approach, distances among minutiae models are used as a basis for the computation of likelihood ratios, which represent the value of the evidence in a given case. Motivated by [3,4], radial triangulationbased forensic palmprint recognition algorithm [10] was proposed and proved to have identification usability and efficiency. However, some problems remain in [10]: 1) The discriminative power of the similarity based on radial triangulation structure is not stable.…”

Section: Introductionmentioning

confidence: 99%