Under controlled synthetic degradations, facial recognition false negatives rise steeply with blur and low resolution, and error rates are highest for Black women, while false positives peak at near-baseline image quality.
Face recognition across non-uniform motion blur, illumination, and pose
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Accuracy and Fairness of Facial Recognition Technology in Low-Quality Police Images: An Experiment With Synthetic Faces
Under controlled synthetic degradations, facial recognition false negatives rise steeply with blur and low resolution, and error rates are highest for Black women, while false positives peak at near-baseline image quality.