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

Kay L. Ritchie, David White, Robin S.S. Kramer, Eilidh Noyes, Rob Jenkins, A. Mike Burton

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Low ‐ quality images are problematic for face identification, for example, when the police identify faces from CCTV images. Here, we test whether face averages, com- prising multiple poor ‐ quality images, can improve both human and computer recogni- tion. 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; Experi- ment 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.
Original languageEnglish
Pages (from-to)671-680
Number of pages10
JournalApplied Cognitive Psychology
Volume32
Issue number6
Early online date17 Aug 2018
DOIs
Publication statusPublished - Nov 2018
Externally publishedYes

    Fingerprint

Cite this

Ritchie, K. L., White, D., Kramer, R. S. S., Noyes, E., Jenkins, R., & Burton, A. M. (2018). Enhancing CCTV: Averages improve face identification from poor-quality images. Applied Cognitive Psychology, 32(6), 671-680. https://doi.org/10.1002/acp.3449