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

TY - JOUR

T1 - Enhancing CCTV

T2 - Averages improve face identification from poor-quality images

AU - Ritchie, Kay L.

AU - White, David

AU - Kramer, Robin S.S.

AU - Noyes, Eilidh

AU - Jenkins, Rob

AU - Burton, A. Mike

N1 - © 2018 John Wiley & Sons, Ltd. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

PY - 2018/11/1

Y1 - 2018/11/1

N2 - 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.

AB - 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.

KW - averages

KW - CCTV

KW - face identification

KW - pixelated images

UR - http://www.scopus.com/inward/record.url?scp=85052381074&partnerID=8YFLogxK

U2 - 10.1002/acp.3449

DO - 10.1002/acp.3449

M3 - Article

AN - SCOPUS:85052381074

SN - 0888-4080

VL - 32

SP - 671

EP - 680

JO - Applied Cognitive Psychology

JF - Applied Cognitive Psychology

IS - 6

ER -