CoChat
Sign Up
Cited by 55

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

Automated face recognition in forensic science: Review and perspectives

Jacquet, Maëlig, Champod, Christophe·2020·Forensic Science International
DOI 10.1016/j.forsciint.2019.110124
Open this paper in CoChat — free account

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.forsciint.2019.110124

Cites

2 of 2 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Compared to equal error rate or ROC curves, Cllr, Cllr Min and ECE plots provide a better representation of both the discrimination power of a model and its calibration performance.

    “Compared to equal error rate or ROC curves, these metrics provide a better representation of both the discrimination power of the model and its calibration performance.”

    From Calibration of score based likelihood ratio estimation in automated forensic facial image comparison (2022) · cites this paper as [16]

    The ECE and cost-of-log-likelihood-ratio section describes ECE plots showing a model before and after calibration, while the DET/EER section says DET plots show discrimination but not calibration. However, it identifies minCllr specifically as a measure of discrimination, not of both characteristics, and our copy does not make the stated comparison with ROC curves. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • In the literature, such calibrations are performed normally as suspect-anchored and trace-anchored, however this type of calibration was not the use case in this study due to only having one sample of each identity in the comparison tests.

    “In the literature, such calibrations are performed normally as suspect-anchored and trace-anchored [16,39], however this type of calibration was not the use case in this study due to only having one sample of each identity in the comparison tests.”

    From Calibration of score based likelihood ratio estimation in automated forensic facial image comparison (2022) · cites this paper as [16]

    The Trace-anchored approach and Source (suspect)-anchored approach sections describe both methods, supporting their identification as approaches in the literature. But the paper discusses them as ways to model score variability, not as the normal forms of calibration; its Suspect-independent/Generic approach section says a generic approach is used in most cases when only one or no reference image is available. The statement about the citing study’s samples is not attributed to this source. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • Forensic facial image comparison lacks a standard method for interpreting the comparison between trace and suspect images.

    “Forensic facial image comparison lacks a methodological standardization and empirical validation.”

    From Calibration of score based likelihood ratio estimation in automated forensic facial image comparison (2022) · cites this paper as [16]

  • No study has yet shown the impact of variations in the choice of the relevant population for automatic face recognition.

    “According to [16], no study has yet shown the impact of variations in the choice of the relevant population for automatic face recognition.”

    From Calibration of score based likelihood ratio estimation in automated forensic facial image comparison (2022) · cites this paper as [16]

  • Automated systems for facial image comparison, especially deep-learning systems, combined with score-based likelihood ratio estimation have great potential to help the forensic expert in the evaluative process.

    “As explored in [40] and [3], automated systems for facial image comparison (especially when based on deep learning) combined with score-based likelihood ratio estimation have a great potential to help the forensic expert in the evaluative process [16].”

    From Calibration of score based likelihood ratio estimation in automated forensic facial image comparison (2022) · cites this paper as [16]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 50

  1. Peacock, 2004, Automatic forensic face recognition from digital images, Sci. Justice, 44, 29, 10.1016/S1355-0306(04)71682-2 · DOI
  2. Rossy, 2013, Integrating forensic information in a crime intelligence database, Forensic Sci. Int., 230, 137, 10.1016/j.forsciint.2012.10.010 · DOI
  3. Dessimoz, 2015, A dedicated framework for weak biometrics in forensic science for investigation and intelligence purposes: the case of facial information, Secur. J., 29, 603, 10.1057/sj.2015.32 · DOI
  4. Zeinstra, 2018, Forensic face recognition as a means to determine strength of evidence: a survey, Forensic Sci. Rev., 30, 23
  5. Milliet, 2014, A forensic science perspective on the role of images in crime investigation and reconstruction, Sci. Justice, 54, 470, 10.1016/j.scijus.2014.07.001 · DOI
  6. Jackson, 2006, The nature of forensic science opinion—a possible framework to guide thinking and practicce in investigation and in court proceedings, Sci. Justice, 46, 33, 10.1016/S1355-0306(06)71565-9 · DOI
  7. Ribaux, 2010, Intelligence-led crime scene processing. Part I: forensic intelligence, Forensic Sci. Int., 195, 10, 10.1016/j.forsciint.2009.10.027 · DOI
  8. Ribaux, 2003, Forensic intelligence and crime analysis, Law Probab. Risk, 2, 47, 10.1093/lpr/2.1.47 · DOI
  9. Ribaux, 2006, The contribution of forensic science to crime analysis and investigation: forensic intelligence, Forensic Sci. Int., 156, 171, 10.1016/j.forsciint.2004.12.028 · DOI
  10. Porter, 2000, An anatomical and photographic technique for forensic facial identification, Forensic Sci. Int., 114, 97, 10.1016/S0379-0738(00)00290-5 · DOI
  11. Moreton, 2011, Investigation into the use of photoanthropometry in facial image comparison, Forensic Sci. Int., 212, 231, 10.1016/j.forsciint.2011.06.023 · DOI
  12. Taigman, 2014, DeepFace: closing the gap to human-level performance in face verification, Conference on Computer Vision and Pattern Recognition, 1701
  13. Schroff, 2015, FaceNet: a unified embedding for face recognition and clustering, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 815
  14. Grother, 2019, Face Recognition Vendor Test (FRVT) Part 3: demographic effects, National Institute of Standards and Technology - NISTIR, 8280
  15. Best-Rowden, 2013, Unconstrained face recognition: establishing baseline human performance via crowdsourcing, IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS), 1
  16. Edmond, 2009, Law’s looking glass: expert identification evidence derived from photographic and video images, Curr. Issues Crim. Justice, 20, 337, 10.1080/10345329.2009.12035817 · DOI
  17. Imwinkelried, 2017, Computer source code: a source of the growing controversy over the reliability of automated forensic techniques, DePaul Law Rev., 66, 97
  18. Geradts, 2018, Digital, big data and computational forensics, Forensic Sci. Res., 3, 179, 10.1080/20961790.2018.1500078 · DOI
  19. O’Toole, 2018, Face space representations in deep convolutional neural networks, Trends Cogn. Sci., 22, 794, 10.1016/j.tics.2018.06.006 · DOI
  20. Parde, 2019, Social trait information in deep convolutional neural networks trained for face identification, Cogn. Sci., 43, e12729, 10.1111/cogs.12729 · DOI
  21. Meuwly, 2017, A guideline for the validation of likelihood ratio methods used for forensic evidence evaluation, Forensic Sci. Int., 276, 142, 10.1016/j.forsciint.2016.03.048 · DOI · Paper page
  22. Champod, 2001, A probabilistic approach to fingerprint evidence, J. Forensic Identif., 51, 101
  23. Evett, 1998, A Bayesian approach to interpreting footwear marks in forensic casework, Sci. Justice, 38, 241, 10.1016/S1355-0306(98)72118-5 · DOI
  24. Lewis, 1984, Philosophy of speaker identification, Police Appl. Speech Tape Record. Anal. – Proc. Inst. Acoust., 6, 69
  25. Bunch, 2013, Application of likelihood ratios for firearm and toolmark analysis, Sci. Justice, 53, 223, 10.1016/j.scijus.2012.12.005 · DOI
  26. Bolck, 2015, Evaluating score- and feature-based likelihood ratio models for multivariate continuous data: applied to forensic MDMA comparison, Law Probab. Risk, 14, 243, 10.1093/lpr/mgv009 · DOI
  27. Davis, 2012, Using subsampling to estimate the strength of handwriting evidence via score-based likelihood ratios, Forensic Sci. Int., 216, 146, 10.1016/j.forsciint.2011.09.013 · DOI
  28. De March, 2020, Bayesian networks and dissonant items of evidence: a case study, Forensic Sci. Int. Genet., 44, 10.1016/j.fsigen.2019.102172 · DOI
  29. Susyanto, 2019, Semiparametric likelihood-ratio-based biometric score level fusion via parametric copula, IET Biom., 8, 277, 10.1049/iet-bmt.2018.5106 · DOI
  30. Nandakumar, 2008, Likelihood ratio-based biometric score fusion, IEEE Trans. Pattern Anal. Mach. Intell., 30, 342, 10.1109/TPAMI.2007.70796 · DOI
  31. Meuwly, 2006, Forensic individualisation from biometric data, Sci. Justice, 46, 205, 10.1016/S1355-0306(06)71600-8 · DOI
  32. Hepler, 2012, Score-based likelihood ratios for handwriting evidence, Forensic Sci. Int., 219, 129, 10.1016/j.forsciint.2011.12.009 · DOI
  33. Neumann, 2009, New perspectives in the use of ink evidence in forensic science: part III: operational applications and evaluation, Forensic Sci. Int., 192, 29
  34. Neumann, 2015, Quantifying the weight of fingerprint evidence through the spatial relationship, directions and types of minutiae observed on fingermarks, Forensic Sci. Int., 248, 154, 10.1016/j.forsciint.2015.01.007 · DOI
  35. Jain, 2012, Face matching and retrieval in forensics applications, IEEE Multimed., 19, 2, 10.1109/MMUL.2012.4 · DOI · Paper page
  36. Kemelmacher-Shlizerman, 2016, The MegaFace benchmark: 1 million faces for recognition at scale, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4873
  37. Ali, 2013, Effect of calibration data on forensic likelihood ratio from a face recognition system, IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS), 1
  38. Phillips, 2005, Overview of the face recognition grand challenge, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 947
  39. Evett, 2000, The impact of the principles of evidence interpretation on the structure and content of statements, Sci. Justice, 40, 233, 10.1016/S1355-0306(00)71993-9 · DOI
  40. Champod, 2009, Evidence interpretation: a logical approach, vol. 2, 968
  41. Ali, 2012, A review of calibration methods for biometric systems in forensic applications, 33rd WIC Symposium on Information Theory in the Benelux
  42. Neumann, 2006, Computation of likelihood ratios in fingerprint identification for configurations of three minutiae, J. Forensic Sci., 51, 1255, 10.1111/j.1556-4029.2006.00266.x · DOI
  43. Lindley, 1979, On the reconciliation of probability assessments, J. R. Stat. Soc. Ser. A, 142, 146, 10.2307/2345078 · DOI
  44. Brümmer, 2006, Application-independent evaluation of speaker detection, Comput. Speech Lang., 20, 230, 10.1016/j.csl.2005.08.001 · DOI
  45. Ramos, 2013, Reliable support: measuring calibration of likelihood ratios, Forensic Sci. Int., 230, 156, 10.1016/j.forsciint.2013.04.014 · DOI · Paper page
  46. Morrison, 2013, Tutorial on logistic-regression calibration and fusion: converting a score to a likelihood ratio, Aust. J. Forensic Sci., 45, 173, 10.1080/00450618.2012.733025 · DOI
  47. Martin, 1997, The DET curve in assessment of detection task performance, Eurospeech, 4, 1895, 10.21437/Eurospeech.1997-504 · DOI
  48. Tippett, 1968, The evidential value of the comparison of paint flakes from sources other than vehicles, J. Forensic Sci. Soc., 8, 61, 10.1016/S0015-7368(68)70442-4 · DOI
  49. Evett, 1996, Statistical analysis of STR data, vol. 6, 79
  50. Ramos, 2013, Information-theoretical assessment of the performance of likelihood ratio computation methods, J. Forensic Sci., 58, 1503, 10.1111/1556-4029.12233 · DOI

Cited by

Sorted by citations

Metadata

Authors
Jacquet, M., & Champod, C.
ORCID
Jacquet, Maëlig
Venue
Forensic Science International
Publisher
Elsevier BV
Published
2020-02
Volume
307
Pages
110124
ISSN
0379-0738
DOI
10.1016/j.forsciint.2019.110124
Cited by
55
References
2
Language
en
Licence

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review