z-logo
Premium
Enhancing CCTV: Averages improve face identification from poor‐quality images
Author(s) -
Ritchie Kay L.,
White David,
Kramer Robin S. S.,
Noyes Eilidh,
Jenkins Rob,
Burton A. Mike
Publication year - 2018
Publication title -
applied cognitive psychology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.719
H-Index - 100
eISSN - 1099-0720
pISSN - 0888-4080
DOI - 10.1002/acp.3449
Subject(s) - artificial intelligence , facial recognition system , face (sociological concept) , computer vision , identification (biology) , computer science , image quality , quality (philosophy) , pattern recognition (psychology) , image (mathematics) , social science , philosophy , botany , epistemology , sociology , biology
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.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here