Abstract
A facial composite generated from an eyewitness’s memory often constitutes the first and only means available for police forces to identify a criminal suspect. To date, commercial computerised systems for constructing facial composites have relied almost exclusively on a feature-based, ‘cut-andpaste’ method whose effectiveness has been fundamentally limited by both the witness’s limited ability to recall and verbalise facial features and by the large dimensionality of the search space. We outline a radically new approach to composite generation which combines a parametric, statistical model of facial appearance with a computational search algorithm based on interactive, evolutionary principles. We describe the fundamental principles on which the new system has been constructed, outline recent innovations in the computational search procedure and also report on the real-world experience of UK police forces who have been using a commercial version of the system.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Turner, J., Pike, G., Towell, N., Kemp, R., Bennett, P.: Making Faces: Comparing E-FIT construction techniques. In: Proceedings of The British Psychological Society, vol. 7, p. 78 (1999)
Solomon, C.J., Gibson, S.J., Pallares-Bejarano, A.: Photographic Quality Facial Composites for Criminal Investigations. In: The 10th Meeting of the International Association for Craniofacia Identification (2002)
Gibson, S.J., Solomon, C.J., Pallares-Bejarano, A., Maylin, M.I.S.: Synthesis of Photographic Quality Facial Composites using Evolutionary Algorithms. In: Proceedings of the British Machine Vision Conference, pp. 221–230 (2003)
Frowd, C.D., Hancock, P.J.B., Carson, D.: EvoFIT: A holistic, evolutionary facial imaging technique for creating composites. ACM Transactions on Applied Psychology (TAP) 1, 1–21 (2004)
Caldwell, C., Johnston, V.S.: Tracking a Criminal Through "Face-Space" with a Genetic Algorithm. In: Belew, R.K., Booker, L.B. (eds.) Proceedings of the Fourth International Conference on Genetic Algorithms, pp. 416–421. Morgan Kauffman Pubs., San Diego (1991)
Cootes, T., Taylor, C.: Statistical models of appearance for medical image analysis and computer vision. In: SPIE Medical Imaging, pp. 236–248 (2001)
Solomon, C.J., Pallares-Bejarano, A., Gibson, S.J.: Non-Linear, Near Photo-Realistic Caricatures using a Parametric Facial Appearance Model. Behaviour Research: Methods, Instrumentation and Computing 37(2), 170–181 (2005)
Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison Wesley, Reading (1989)
Pallares-Bejarano, A.: Evolutionary Algorithms for Synthesis of Facial Composites, Ph.D thesis, University of Kent, UK (2006)
Gibson, S.J., Pallares-Bejarano, A., Maylin, M.I.S., Solomon, C.J.: The Generation of Facial Composites using an Evolutionary Algorithm. In: Procedings of 6th International Conference on Recent Advances in Soft Computing (best paper award), Canterbury (2006)
Scandrett, C.M., Solomon, C.J., Gibson, S.J.: A Person-Specific, Rigorous Aging Model of the Human Face. Pattern Recognition Letters 27(15), 1776–1787 (2006)
Benson, P.J., Perrett, D.I.: Extracting Prototypical Facial Images from Exemplars. Perception 22, 257–262 (1993)
Police Professional, Investigative Practice Journal, 21-24 (January 24, 2008)
Fisher, R.P., Geiselman, R.E.: Memory Enhancing Techniques for Investigative Interviewing. Charles Thomas, Springfield (1992)
Frowd, C.D., Bruce, V., Smith, A., Hancock, P.J.B.: Improving the quality of facial composites using a holistic cognitive interview. Journal of Experimental Psychology: Applied 14, 276–287 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Solomon, C., Gibson, S., Maylin, M. (2009). A New Computational Methodology for the Construction of Forensic, Facial Composites. In: Geradts, Z.J.M.H., Franke, K.Y., Veenman, C.J. (eds) Computational Forensics. IWCF 2009. Lecture Notes in Computer Science, vol 5718. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03521-0_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-03521-0_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03520-3
Online ISBN: 978-3-642-03521-0
eBook Packages: Computer ScienceComputer Science (R0)