CoChat
Sign Up
Cited by 18

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Enhancing CCTV: Averages improve face identification from poor-quality images

Ritchie, Kay L., White, David, Kramer, Robin S. S., Noyes, Eilidh, Jenkins, Rob, Burton, A. Mike·2018·Applied Cognitive Psychology
DOI 10.1002/acp.3449
Open this paper in CoChat — free account

Abstract

Summary: Low‐quality images are problematic for face identification, for example, when the police identify faces from CCTV images. Here, we test whether face averages, comprising multiple poor‐quality images, can improve both human and computer recognition. We created averages from multiple pixelated or nonpixelated images and compared accuracy using these images and exemplars. To provide a broad assessment of the potential benefits of this method, we tested human observers (n = 88; Experiment 1), and also computer recognition, using a smartphone application (Experiment 2) and a commercial one‐to‐many face recognition system used in forensic settings (Experiment 3). The third experiment used large image databases of 900 ambient images and 7,980 passport images. In all three experiments, we found a substantial increase in performance by averaging multiple pixelated images of a person's face. These results have implications for forensic settings in which faces are identified from poor‐quality images, such as CCTV.

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 · 10.1002/acp.3449

Cites

1 of 1 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?

  • Highly pixelated images can reduce face matching abilities by up to 50% in trained individuals when compared to a high-quality image sample.

    “Highly pixelated images can reduce face matching abilities by up to 50% in trained individuals when compared to a high-quality image sample [94,98].”

    From Forensic Facial Comparison: Current Status, Limitations, and Future Directions (2021) · cites this paper as [94]

    The Experiment 1 Results and Discussion report that pixelated images were harder to match than unpixelated images. But the Participants section (p. 5) describes university volunteers, not trained individuals, and the text does not report a reduction of up to 50%. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

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: 42

  1. Beveridge J. R. Phillips P. J. Givens G. H. Draper B. A. Teli M. N. &Bolme D. S.(2011).When high‐quality face images match poorly. IEEE proceedings of the international conference on automatic face and gesture recognition 572–578. · DOI
  2. 10.1002/acp.2970 · DOI · Paper page
  3. Boyle M. Edwards C. &Greenberg S.(2000).The effects of filtered video on awareness and privacy.Proceedings of the ACM Conference on Computer Supported Cooperative Work 1–10. · DOI
  4. 10.1037/1076-898X.5.4.339 · DOI · Paper page
  5. 10.1037/0021-9010.87.5.894 · DOI
  6. Buciu I. &Gacsadi A.(2011). Noise suppression methods for low quality images with application to face recognition.IEEE Proceedings ELMAR 21‐24.
  7. 10.1016/j.cogpsych.2005.06.003 · DOI
  8. 10.1111/cogs.12231 · DOI
  9. 10.1111/1467-9280.00144 · DOI · Paper page
  10. 10.1348/000712600161907 · DOI
  11. 10.1002/acp.1490 · DOI · Paper page
  12. 10.5334/pb-47-4-261 · DOI
  13. Fronthaler H. Kollreider K. &Bigun J.(2006).Automatic image quality assessment with application in biometrics. IEEE Conference on Computer Vision and Pattern Recognition 30–35.
  14. Frowd C. D. Bruce V. Plenderleith Y. &Hancock P. J. B.(2006).Improving target identification using pairs of composite faces constructed by the same person. IEE Conference on Crime and Security 386–395 IET: London. · DOI
  15. Gross R. Sweeney L. De la Torre F. &Baker S.(2006).Model‐based face de‐identification.IEEE Conference on Computer Vision and Pattern Recognition Workshop 161–168.
  16. Grother P. &Ngan M.(2014).Face Recognition Vendor Test (FRVT). Performance of face identification algorithms. NIST Interagency Report 8009. · DOI · Paper page
  17. 10.1007/s10979-006-9007-2 · DOI
  18. Huang G., 2007, Labeled faces in the wild: A database for studying face recognition in unconstrained environments, 07
  19. 10.1126/science.1149656 · DOI
  20. Keval H. &Sasse M. A.(2008).Can we ID from CCTV? Image quality in digital CCTV and facial identification performance.Proceedings of SPIE International Society for Optical Engineering 6982. · DOI · Paper page
  21. Kitahara I. Kogure K. &Hagita N.(2004).Stealth vision for protecting privacy. IEEE proceedings of the 17th international conference on patter recognition 404–407. · DOI
  22. 10.3758/s13428-016-0837-7 · DOI
  23. 10.1037/rev0000048 · DOI
  24. 10.1002/1099-0720(200101/02)15:1<101::AID-ACP697>3.0.CO;2-7 · DOI
  25. Luo H., 2004, IEEE proceedings international conference on image processing, 2973
  26. 10.1109/TKDE.2005.32 · DOI
  27. 10.1111/1556-4029.12660 · DOI · Paper page
  28. 10.1109/TPAMI.2007.1107 · DOI
  29. 10.1016/j.eswa.2015.01.041 · DOI
  30. Phillips P. J. Flynn P. J. Scruggs T. Bowyer K. W. &Worek W.(2006).Preliminary face recognition grand challenge results. Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition 15–24. · DOI
  31. Phillips P. J. Hill M. Q. Swindle J. A. &O'Toole A. J.(2015).Human and algorithm performance on the PaSC face recognition challenge. IEEE 7th International Conference on Biometrics Theory Applications and Systems 1–8. · DOI
  32. 10.1109/34.879790 · DOI · Paper page
  33. 10.1016/j.imavis.2013.12.002 · DOI
  34. 10.1016/j.cognition.2015.05.002 · DOI · Paper page
  35. 10.1371/journal.pone.0119460 · DOI
  36. Rudrani S., 2011, Face recognition on low quality surveillance images by compensating degradation, Image Analysis and Recognition, 6754, 212
  37. 10.1109/38.946630 · DOI
  38. 10.1016/j.scijus.2015.04.010 · DOI
  39. 10.1037/xap0000009 · DOI
  40. 10.1007/978-3-319-50673-9_9 · DOI
  41. 10.1098/rspb.2015.1292 · DOI · Paper page
  42. 10.1145/954339.954342 · DOI

Cited by

Sorted by citations

Metadata

Authors
Ritchie, K. L., White, D., Kramer, R. S. S., Noyes, E., Jenkins, R., & Burton, A. M.
Affiliations
  • School of Psychology University of Lincoln Lincoln UK
  • School of Psychology University of New South Wales Sydney Australia
  • Department of Psychology University of York York UK
ORCID
Venue
Applied Cognitive Psychology
Publisher
Wiley
Published
2018-08-17
Volume
32
Issue
6
Pages
671-680
ISSN
  • 0888-4080
  • 1099-0720
DOI
10.1002/acp.3449
Cited by
18
References
1
Language
en
Licence
onlinelibrary.wiley.com/termsAndConditions#vor (vor)
Funders
  • Economic and Social Research Council (ES/J022950/1 to AMB)
  • FP7 Ideas: European Research Council (323262 to AMB)

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