Understanding familiar face recognition for 3D scanned images

The importance of internal and external facial features

Anna Williams, Helen York, Charlie D. Frowd

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Clay or computerised facial reconstructions are often presented to the public for recognition without information about the external features of a head (hair, ears and neck) as these are thought to be potentially distracting or even misleading. In this context, the mechanisms of face recognition are poorly understood, but existing research using photographs of familiar faces suggests that external features play an important role for recognition, and external features may even be necessary for recognition to occur at all. The current research aimed to determine the contribution that external features make to the recognition of a familiar face rendered in 3D. It will also determine whether the inclusion or exclusion of external features from a reconstruction is likely to be beneficial. Volunteers were asked to name images of 3D faces of people known to them, presented as either full face 3D surface scans, or where the internal or external features had been removed. As was expected, a clear correlation was found between information presented in the scans and the recognition rate, with participants correctly naming full face images most often and images of external features least often. Logistic regression analysis demonstrated a significant linear trend in recognition rate in the order of external features, internal features and full face. Incorrect naming also increased linearly, indicating that participants were more likely to offer a name (correct or otherwise) when more useful facial information was provided.

Original languageEnglish
Title of host publicationProceedings - 3rd International Conference on Emerging Security Technologies, EST 2012
PublisherIEEE
Pages27-32
Number of pages6
ISBN (Electronic)9780769547916
ISBN (Print)9781467324489
DOIs
Publication statusPublished - 11 Oct 2012
Externally publishedYes
Event3rd International Conference on Emerging Security Technologies - Lisbon, Portugal
Duration: 5 Sep 20127 Sep 2012

Conference

Conference3rd International Conference on Emerging Security Technologies
Abbreviated titleEST 2012
CountryPortugal
CityLisbon
Period5/09/127/09/12

Fingerprint

Face recognition
Regression analysis
Logistics
Clay

Cite this

Williams, A., York, H., & Frowd, C. D. (2012). Understanding familiar face recognition for 3D scanned images: The importance of internal and external facial features. In Proceedings - 3rd International Conference on Emerging Security Technologies, EST 2012 (pp. 27-32). [6328076] IEEE. https://doi.org/10.1109/EST.2012.36
Williams, Anna ; York, Helen ; Frowd, Charlie D. / Understanding familiar face recognition for 3D scanned images : The importance of internal and external facial features. Proceedings - 3rd International Conference on Emerging Security Technologies, EST 2012. IEEE, 2012. pp. 27-32
@inproceedings{170cf977753344e5bc0081418f654c0f,
title = "Understanding familiar face recognition for 3D scanned images: The importance of internal and external facial features",
abstract = "Clay or computerised facial reconstructions are often presented to the public for recognition without information about the external features of a head (hair, ears and neck) as these are thought to be potentially distracting or even misleading. In this context, the mechanisms of face recognition are poorly understood, but existing research using photographs of familiar faces suggests that external features play an important role for recognition, and external features may even be necessary for recognition to occur at all. The current research aimed to determine the contribution that external features make to the recognition of a familiar face rendered in 3D. It will also determine whether the inclusion or exclusion of external features from a reconstruction is likely to be beneficial. Volunteers were asked to name images of 3D faces of people known to them, presented as either full face 3D surface scans, or where the internal or external features had been removed. As was expected, a clear correlation was found between information presented in the scans and the recognition rate, with participants correctly naming full face images most often and images of external features least often. Logistic regression analysis demonstrated a significant linear trend in recognition rate in the order of external features, internal features and full face. Incorrect naming also increased linearly, indicating that participants were more likely to offer a name (correct or otherwise) when more useful facial information was provided.",
keywords = "3D scans, facial features, Facial recognition",
author = "Anna Williams and Helen York and Frowd, {Charlie D.}",
year = "2012",
month = "10",
day = "11",
doi = "10.1109/EST.2012.36",
language = "English",
isbn = "9781467324489",
pages = "27--32",
booktitle = "Proceedings - 3rd International Conference on Emerging Security Technologies, EST 2012",
publisher = "IEEE",

}

Williams, A, York, H & Frowd, CD 2012, Understanding familiar face recognition for 3D scanned images: The importance of internal and external facial features. in Proceedings - 3rd International Conference on Emerging Security Technologies, EST 2012., 6328076, IEEE, pp. 27-32, 3rd International Conference on Emerging Security Technologies, Lisbon, Portugal, 5/09/12. https://doi.org/10.1109/EST.2012.36

Understanding familiar face recognition for 3D scanned images : The importance of internal and external facial features. / Williams, Anna; York, Helen; Frowd, Charlie D.

Proceedings - 3rd International Conference on Emerging Security Technologies, EST 2012. IEEE, 2012. p. 27-32 6328076.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Understanding familiar face recognition for 3D scanned images

T2 - The importance of internal and external facial features

AU - Williams, Anna

AU - York, Helen

AU - Frowd, Charlie D.

PY - 2012/10/11

Y1 - 2012/10/11

N2 - Clay or computerised facial reconstructions are often presented to the public for recognition without information about the external features of a head (hair, ears and neck) as these are thought to be potentially distracting or even misleading. In this context, the mechanisms of face recognition are poorly understood, but existing research using photographs of familiar faces suggests that external features play an important role for recognition, and external features may even be necessary for recognition to occur at all. The current research aimed to determine the contribution that external features make to the recognition of a familiar face rendered in 3D. It will also determine whether the inclusion or exclusion of external features from a reconstruction is likely to be beneficial. Volunteers were asked to name images of 3D faces of people known to them, presented as either full face 3D surface scans, or where the internal or external features had been removed. As was expected, a clear correlation was found between information presented in the scans and the recognition rate, with participants correctly naming full face images most often and images of external features least often. Logistic regression analysis demonstrated a significant linear trend in recognition rate in the order of external features, internal features and full face. Incorrect naming also increased linearly, indicating that participants were more likely to offer a name (correct or otherwise) when more useful facial information was provided.

AB - Clay or computerised facial reconstructions are often presented to the public for recognition without information about the external features of a head (hair, ears and neck) as these are thought to be potentially distracting or even misleading. In this context, the mechanisms of face recognition are poorly understood, but existing research using photographs of familiar faces suggests that external features play an important role for recognition, and external features may even be necessary for recognition to occur at all. The current research aimed to determine the contribution that external features make to the recognition of a familiar face rendered in 3D. It will also determine whether the inclusion or exclusion of external features from a reconstruction is likely to be beneficial. Volunteers were asked to name images of 3D faces of people known to them, presented as either full face 3D surface scans, or where the internal or external features had been removed. As was expected, a clear correlation was found between information presented in the scans and the recognition rate, with participants correctly naming full face images most often and images of external features least often. Logistic regression analysis demonstrated a significant linear trend in recognition rate in the order of external features, internal features and full face. Incorrect naming also increased linearly, indicating that participants were more likely to offer a name (correct or otherwise) when more useful facial information was provided.

KW - 3D scans

KW - facial features

KW - Facial recognition

UR - http://www.scopus.com/inward/record.url?scp=84869406871&partnerID=8YFLogxK

U2 - 10.1109/EST.2012.36

DO - 10.1109/EST.2012.36

M3 - Conference contribution

SN - 9781467324489

SP - 27

EP - 32

BT - Proceedings - 3rd International Conference on Emerging Security Technologies, EST 2012

PB - IEEE

ER -

Williams A, York H, Frowd CD. Understanding familiar face recognition for 3D scanned images: The importance of internal and external facial features. In Proceedings - 3rd International Conference on Emerging Security Technologies, EST 2012. IEEE. 2012. p. 27-32. 6328076 https://doi.org/10.1109/EST.2012.36