An international survey of applied face-matching training courses

Moreton, Reuben; Havard, Catriona; Strathie, Ailsa; Pike, Graham

doi:10.1016/j.forsciint.2021.110947

Cited by 6 publications

(10 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This supports our earlier finding that specialized training programs and teaching observers with varied instances will increase detection accuracy. This observation is also in line with research done on the effectiveness of courses in facial comparisons, where the researchers suggest that examination-based training could be an important part of a training program [45].…”

Section: Discussionsupporting

confidence: 87%

Analyzing Human Observer Ability in Morphing Attack Detection—Where Do We Stand?

Godage

Lovasdaly

Venkatesh

et al. 2023

IEEE Trans. Technol. Soc.

View full text Add to dashboard Cite

Morphing attacks are based on the technique of digitally fusing two (or more) face images into one, with the final visage resembling the contributing faces. Morphed images not only pose a challenge to Face-Recognition Systems (FRS) but also challenge experienced human observers due to high quality, postprocessing eliminating any visible artifacts, and further the printing and scanning process. Few studies have concentrated on examining how human observers can recognize morphing attacks, even as several publications have examined the susceptibility of automated FRS to morphing attacks and offered morphing attack detection (MAD) approaches. MAD approaches base their decisions either on a single image with no reference to compare against (Single-Image MAD (S-MAD)) or using a reference image (Differential MAD (D-MAD)). One prevalent misconception is that an examiner's or observer's capacity for facial morph detection depends on their subject expertise, experience, and familiarity with the issue. No works have reported the specific results of observers who regularly verify identity (ID) documents for their jobs. As human observers are involved in checking ID documents having facial images, a lapse in their competence can result in significant societal challenges. To assess the observers' proficiency, this research first builds a new benchmark database of realistic morphing attacks from 48 different subjects, resulting in 400 morphed images. Unlike the previous works, we also capture images from Automated Border Control (ABC) gates to mimic realistic border-crossing scenarios in the D-MAD setting with 400 probe images, to study the ability of human observers to detect morphed images. A new dataset of 180 morphing images is also produced to research human capacity in the S-MAD environment. In addition to creating a new evaluation platform to conduct S-MAD and D-MAD analysis, the study employs 469 observers for D-MAD and 410 observers for S-MAD who are primarily governmental employees from more than 40 countries, along with 103 control group members who are not examiners. The analysis offers intriguing insights and highlights the lack of expertise and failure to recognize a sizable number of morphing attacks by experienced observers. Human observers tend to detect morphed images to a lower accuracy as compared to the four automated MAD algorithms evaluated in this work. The results of this study are intended to aid in the development of training programs that will prevent security failures while determining whether an image is bona fide or altered.

show abstract

Section: Discussionsupporting

confidence: 87%

Analyzing Human Observer Ability in Morphing Attack Detection—Where Do We Stand?

Godage

Lovasdaly

Venkatesh

et al. 2023

IEEE Trans. Technol. Soc.

View full text Add to dashboard Cite

show abstract

“…Five forensic facial examiners from a UK‐based organisation took part in this experiment (mean age = 34.4 years, SD = 1.8, range 32–37 years, 1 male), with mean experience in facial comparison of 34.8 months ( SD = 31.6, range 6–84 months). All five forensic facial examiners had received formal training in facial image comparison, including recommended topics in anatomy, image science and processing, and methods of comparison (see Moreton et al, 2021), and had either completed or were undergoing a 6‐month period of workplace mentoring with a more senior examiner. In addition, eight fingerprint analysts from the same organisation (mean age = 41.3 years, SD = 7.1, range 32–50 years, 3 males) with mean experience in fingerprint comparison of 162 months ( SD = 35.6, range 108–204 months), served as a forensically‐trained control group.…”

Section: Methodsmentioning

confidence: 99%

“…This is in stark contrast to how untrained observers compare faces in a matter of only a few seconds (Bindemann et al, 2016; Fysh & Bindemann, 2017; Özbek & Bindemann, 2011; Wirth & Carbon, 2017), as well as the occupational demands of professionals such as passport control officers, who also must perform this task quickly. Training practices for facial examiners vary between different organisations, but commonly include lengthy mentorship, performance monitoring and feedback, to become proficient in morphological analysis (Moreton et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Facial comparison behaviour of forensic facial examiners

Claydon

Fysh

Prunty

et al. 2022

Applied Cognitive Psychology

Self Cite

View full text Add to dashboard Cite

Facial examiners make visual comparisons of face images to establish the identities of persons in police investigations. This study utilised eye-tracking and an individual differences approach to investigate whether these experts exhibit specialist viewing behaviours during identification, by comparing facial examiners with forensic fingerprint analysts and untrained novices across three tasks. These comprised of face matching under unlimited (Experiment 1) and time-restricted viewing (Experiment 2), and with a feature-comparison protocol derived from examiner casework procedures (Experiment 3). Facial examiners exhibited individual differences in facial comparison accuracy and did not consistently outperform fingerprint analysts and novices. Their behaviour was also marked by similarities to the comparison groups in terms of how faces were viewed, as evidenced from eye movements, and how faces were perceived, based on the made feature judgements and identification decisions. These findings further understanding of how facial comparisons are performed and clarify the nature of examiner expertise.

show abstract

“…Facial forensic examinerswho analyse similarities and differences between face images to provide evidentiary reports for police investigations and criminal trialsoutperform standard participant groups by roughly the same margin 57,164,174,175 as selectively-recruited, but untrained, super-recognisers. In contrast to super-recognisers' quick and intuitive recognition ability, forensic abilities are founded on years of deliberate training in comparing images of unfamiliar faces 176 and involve slow, analytic comparison 174,175 .…”

Section: Forensic Face Identificationmentioning

confidence: 99%

“…Training in applied settings tends to be tailored to the specific task of matching unfamiliar faces 176 . A large-scale evaluation of professional training courses showed no learning beyond the specific faces used in each course 169 .…”

Section: [H1] Training Typical Face Abilitiesmentioning

confidence: 99%

Individual differences and the multidimensional nature of face perception

White

Burton

2022

Nat Rev Psychol

View full text Add to dashboard Cite

Face perception is critical to social interactions, yet people vary in how easily they can recognise their friends, verify an identification document, or notice someone's smile. There are widespread differences in people's abilities to recognise faces and research has particularly focused on exceptionally good or poor recognition performance. In this Review, we synthesise literature on individual differences in face processing across different tasks including identification and estimates of emotional state and social attributes. The individual differences approach has considerable untapped potential for theoretical progress in understanding the perceptual and cognitive organisation of face processing. This approach also has practical consequencesfor example, in determining who is best suited to check passports. We also discuss the underlying structural and anatomical predictors of face perception ability. Furthermore, we highlight problems of measurement that pose challenges for the effective study of individual differences. Finally, we note that research in individual differences rarely addresses perception of familiar faces. Despite people's everyday experience of being ‗good' or ‗bad' with faces, a theory of how people recognise their friends remains elusive. [H1] IntroductionFaces provide many types of information. Using faces, people can recognise others they know and also quite accurately estimate the age, gender or health of strangers and friends. Faces can also be used to judge transient states, for example someone's mood, focus of attention, or speech patterns. The multiple sources of information available in a face are critical for social behaviour, enabling people to identify someone as family, friend or colleague, and to decide whether they should speak to, hug, or stay away from them. These decisions are made quickly and easily, often without reflection. However, these remarkable abilities in face processing are not distributed equally across people.Widespread differences in face perception between individuals have become an important research focus for three reasons. First, everyday experience suggests that some people are better at face perception than others, and some people have strong beliefs about whether they are ‗good with faces'.Second, given the wide variety of information available in a face, much theoretical work focuses on whether the processes underlying different perceptual decisions are independent1 1 . Individual differences techniques are well-suited to addressing these questions in both face processing 2,3 , and other areas of cognition research 4,5 . Third, face processing research has a good track record of using converging evidence to build theory 6-8 . Individual differences methodology can be recruited alongside evidence from experimental psychology, neuroscience, neuropsychology and computational modelling to make significant progress in the field.Research on individual differences in face processing has tended to focus on identity processing.Tests have been designed that mea...

show abstract

An international survey of applied face-matching training courses

Cited by 6 publications

References 33 publications

Analyzing Human Observer Ability in Morphing Attack Detection—Where Do We Stand?

Analyzing Human Observer Ability in Morphing Attack Detection—Where Do We Stand?

Facial comparison behaviour of forensic facial examiners

Individual differences and the multidimensional nature of face perception

Contact Info

Product

Resources

About