Skip to main content Accessibility help
×
Hostname: page-component-848d4c4894-sjtt6 Total loading time: 0 Render date: 2024-07-03T15:19:56.152Z Has data issue: false hasContentIssue false

Chapter 3 - EFIT-V

Evolutionary algorithms and computer composites

Published online by Cambridge University Press:  05 May 2012

Caroline Wilkinson
Affiliation:
University of Dundee
Christopher Rynn
Affiliation:
University of Dundee
Get access

Summary

Introduction

In the event of a crime, police officers often rely on a witness to provide a comprehensive account of the incident. In some circumstances, the witness has to convey a description of the perpetrator based only on a brief encounter. The pertinent question is how is it possible to accurately convey the perpetrator’s face when the image only exists as a memory in the witness’s mind? This corresponds well to the typical circumstances under which a trained police officer will subsequently work with the victim (or other witness to a crime) in an attempt to produce a facial likeness or facial composite of the perpetrator. Unless the witness is a gifted artist it is unlikely that he or she will be able to provide a reliable sketch of the offender/perpetrator. Typically, assuming of course that the attacker is unknown to the witness, he or she will first be asked to provide a detailed verbal description of the attacker and to recount the incident in as much detail as possible. When the interview is complete, an attempt is then made to produce a likeness under the guidance of a specially trained operator. Whilst sketch artists are still used widely in the USA, this process will most likely (in the UK at least) use some form of computerised facial composite system. A facial composite system is a tool designed to allow the expression of the facial appearance retained in the witness’s memory in some tangible form, such as a digital image or computer print-out. The desired outcome is that the generated composite be of sufficient accuracy that subsequent display to members of the public will result in direct recognition and that the details of the suspect will be supplied to the police. In many cases, a generated composite may not be accurate enough to produce a definite ‘hit’ but may nonetheless provoke members of the public who recognise basic similarities to provide the names of possible suspects. In most cases, it is the combination of the composite with other basic information such as age, build, domicile and the type of crime that results in the provision of suspect names.

Type
Chapter
Information
Publisher: Cambridge University Press
Print publication year: 2012

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Benson, P. J.Perrett, D. I. 1993 Extracting prototypical facial images from exemplarsPerception 22 257CrossRefGoogle ScholarPubMed
Brunelli, R.Mich, O. 1996 SpotIt! An interactive identikit systemGraphical Models and Image Processing: GMIP 58 399CrossRefGoogle Scholar
Burt, D. M.Perrett, D. I. 1995 Perception of age in adult caucasian male faces: computer graphic manipulation of shape and colour informationRoyal Society Proceedings B 259 137CrossRefGoogle ScholarPubMed
Caldwell, C.Johnston, V. S. 1991 Tracking a criminal suspect through facespace with a genetic algorithmProceedings of the Fourth International Conference on Genetic Algorithms416Morgan KaufmannGoogle Scholar
Cootes, T. F.Cooper, D.Taylor, C.Graham, J. 1995 Active shape models – their training and applicationComputer Vision and Image Understanding 61 38CrossRefGoogle Scholar
Cootes, T. F.Edwards, G. J.Taylor, C. J. 1998 Active appearance modelsBurkhardt, H.Neumann, B.Proceedings of the European Conference on Computer Vision484BerlinSpringerGoogle Scholar
Cootes, T. F.Taylor, C. J. 2001 Statistical models of appearance for computer visionTechnical Report, Imaging Science and Biomedical EngineeringUniversity of Manchester, UKGoogle Scholar
Cootes, T. F.Taylor, C. J.Cooper, D. H.Graham, J. 1992 Training models of shape from sets of examplesBritish Machine Vision Conference918Google Scholar
DiPaolo, S. 2002
Frowd, C. D.Hancock, P. J. B.Bruce, V. 2010 Howells, G.Sirlantzis, K.Stoica, A.Huntsberger, T.Arslan, A. T.36
Gibson, S. J.Solomon, C. J.Maylin, M. I. S.Clark, C. 2009 New methodology in facial composite construction: from theory to practiceInternational Journal of Electronic Security and Digital Forensics 2 156CrossRefGoogle Scholar
Gibson, S. J.Solomon, C. J.Pallares-Bejarano, A. 2003 Harvey, R.Bangham, J. A.221
Hancock, P. J. B. 2000 Evolving faces from principal componentsBehaviour Research Methods, Instruments and Computers 32 327CrossRefGoogle ScholarPubMed
Hancock, P. J. B.Burton, A. M.Bruce, V. 1996 Face processing: human perception and principal components analysisMemory and Cognition 24 26CrossRefGoogle ScholarPubMed
Holland, J. H. 1975 Adaptation in Natural and Artificial SystemsAnn Arbor, MIUniversity of Michigan PressGoogle Scholar
Lanitis, A.Taylor, C.Cootes, T. F. 2002 Toward automatic simulation of aging effects on face imagesIEEE Transactions on Pattern Analysis and Machine Intelligence 24 442CrossRefGoogle Scholar
Pallares-Bejarano, A. 2006 Evolutionary Algorithms for Facial Composite SynthesisUniversity of KentGoogle Scholar
Penry, J 1971 Looking at Faces and Remembering Them: A Guide to Facial IdentificationLondonElek BooksGoogle Scholar
Ramanathan, N.Chellappa, R. 2005 Face verification across age progressionIEEE Computer Vision and Pattern Recognition 2 462Google Scholar
Scandrett, C. M.Solomon, C. J.Gibson, S. J. 2006 A person-specific rigorous aging model of the human faceSpecial Issue Pattern Recognition Letters: Vision for Crime Detection and Prevention 27 1776CrossRefGoogle Scholar
Sims, K. 1991 Artificial evolution for computer graphicsComputer Graphics 25 319CrossRefGoogle Scholar
Sirovich, L.Kirby, M. 1987 Low dimensional procedure for the characterization of human facesJournal of the Optical Society of America 4 519CrossRefGoogle ScholarPubMed
Solomon, C. J.Gibson, S. J.Maylin, M. I. S. 2009 A new computational methodology for the construction of forensic, facial compositesComputational Forensics, Lecture Notes in Computer Science 5718 67CrossRefGoogle Scholar
Stegmann, M. 2000 Active Appearance Models: Theory, Extensions and CasesDepartment of Mathematical Modelling, Technical University of DenmarkLyngby, DenmarkGoogle Scholar
Tanaka, J. W.Farah, M. J. 1993 Parts and wholes in face recognitionQuarterly Journal of Experimental Psychology 46A 225CrossRefGoogle Scholar
Tiddeman, B. P.Burt, M.Perrett, D. I. 2001 Prototyping and transforming facial textures for perception researchIEEE Computer Graphics and Applications 21 42CrossRefGoogle Scholar
Tredoux, C.Rosenthal, J.Da Costa, L.Nunez, D. 1999 Reconstructing Faces with an Eigenface Composite SystemSARMAC IIIBoulder, ColoradoGoogle Scholar

Save book to Kindle

To save this book to your Kindle, first ensure coreplatform@cambridge.org is added to your Approved Personal Document E-mail List under your Personal Document Settings on the Manage Your Content and Devices page of your Amazon account. Then enter the ‘name’ part of your Kindle email address below. Find out more about saving to your Kindle.

Note you can select to save to either the @free.kindle.com or @kindle.com variations. ‘@free.kindle.com’ emails are free but can only be saved to your device when it is connected to wi-fi. ‘@kindle.com’ emails can be delivered even when you are not connected to wi-fi, but note that service fees apply.

Find out more about the Kindle Personal Document Service.

Available formats
×

Save book to Dropbox

To save content items to your account, please confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account. Find out more about saving content to Dropbox.

Available formats
×

Save book to Google Drive

To save content items to your account, please confirm that you agree to abide by our usage policies. If this is the first time you use this feature, you will be asked to authorise Cambridge Core to connect with your account. Find out more about saving content to Google Drive.

Available formats
×