1. Fraudulent ID using face morphs: Experiments on human and automatic recognition
- Author
-
David J. Robertson, A. Mike Burton, and Robin S. S. Kramer
- Subjects
Computer science ,Speech recognition ,Social Sciences ,lcsh:Medicine ,02 engineering and technology ,Facial recognition system ,Cognition ,Learning and Memory ,C810 Applied Psychology ,0202 electrical engineering, electronic engineering, information engineering ,Medicine and Health Sciences ,Psychology ,National Security ,lcsh:Science ,Multidisciplinary ,05 social sciences ,Pattern Recognition, Visual ,Engineering and Technology ,020201 artificial intelligence & image processing ,Female ,Anatomy ,Research Article ,Adult ,Matching (statistics) ,Computer and Information Sciences ,C850 Cognitive Psychology ,Adolescent ,Imaging Techniques ,Political Science ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,Equipment ,BF ,Research and Analysis Methods ,Face Recognition ,050105 experimental psychology ,Young Adult ,Memory ,Reaction Time ,Humans ,0501 psychology and cognitive sciences ,Computer Security ,Communication Equipment ,lcsh:R ,Cognitive Psychology ,Biology and Life Sciences ,Recognition, Psychology ,C830 Experimental Psychology ,C800 Psychology ,Identity fraud ,Face (geometry) ,Face ,Cognitive Science ,Perception ,lcsh:Q ,Cell Phones ,Electronics ,Head ,Neuroscience - Abstract
Matching unfamiliar faces is known to be difficult, and this can give an opportunity to those engaged in identity fraud. Here we examine a relatively new form of fraud, the use of photo-ID containing a graphical morph between two faces. Such a document may look sufficiently like two people to serve as ID for both. We present two experiments with human viewers, and a third with a smartphone face recognition system. In Experiment 1, viewers were asked to match pairs of faces, without being warned that one of the pair could be a morph. They very commonly accepted a morphed face as a match. However, in Experiment 2, following very short training on morph detection, their acceptance rate fell considerably. Nevertheless, there remained large individual differences in people's ability to detect a morph. In Experiment 3 we show that a smartphone makes errors at a similar rate to 'trained' human viewers-i.e. accepting a small number of morphs as genuine ID. We discuss these results in reference to the use of face photos for security.
- Published
- 2017