Evolving the Face of a Criminal: How to Search a Face Space More Effectively

Witnesses and victims of serious crime are often required to construct a facial composite, a visual likeness of a suspect's face. The traditional method is for them to select individual facial features to build a face, but often these images are of poor quality. We have developed a new method whereby witnesses repeatedly select instances from an array of complete faces and a composite is evolved over time by searching a face model built using PCA. While past research suggests that the new approach is superior, performance is far from ideal. In the current research, face models are built which match a witness's description of a target. It is found that such 'tailored' models promote better quality composites, presumably due to a more effective search, and also that smaller models may be even better. The work has implications for researchers who are using statistical modelling techniques for recognising faces.

[1]  Vicki Bruce,et al.  The relative importance of external and internal features of facial composites. , 2007, British journal of psychology.

[2]  H. K. Garg,et al.  Maximum-likelihood detection in DWT domain image watermarking using Laplacian modeling , 2005, IEEE Signal Processing Letters.

[3]  P. Hancock,et al.  Robust representations for face recognition: The power of averages , 2005, Cognitive Psychology.

[4]  Charlie D. Frowd,et al.  Improving Target Identification Using Pairs of Composite Faces Constructed by the Same Person , 2006 .

[5]  Charlie D. Frowd,et al.  Adding holistic dimensions to a facial composite system , 2006, 7th International Conference on Automatic Face and Gesture Recognition (FGR06).

[6]  V. Bruce,et al.  Recognition of unfamiliar faces , 2000, Trends in Cognitive Sciences.

[7]  Lahouari Ghouti,et al.  Protecting Fingerprint Data Using Watermarking , 2006, First NASA/ESA Conference on Adaptive Hardware and Systems (AHS'06).

[8]  David Nunez,et al.  Face reconstruction using a configural, eigenface-based composite system , 1999 .

[9]  P J Hancock,et al.  Evolving faces from principal components , 2000, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[10]  V. Bruce,et al.  Face processing: Human perception and principal components analysis , 1996, Memory & cognition.

[11]  G Davies,et al.  Facial composite production: a comparison of mechanical and computer-driven systems. , 2000, The Journal of applied psychology.

[12]  H. Ellis,et al.  Identification of Familiar and Unfamiliar Faces from Internal and External Features: Some Implications for Theories of Face Recognition , 1979, Perception.

[13]  Ronald P. Fisher,et al.  Enhancement of Eyewitness Memory with the Cognitive Interview , 1986 .

[14]  Charlie D. Frowd,et al.  EvoFIT: A holistic, evolutionary facial imaging technique for creating composites , 2004, TAP.

[15]  Christopher J. Solomon,et al.  Synthesis of Photographic Quality Facial Composites using Evolutionary Algorithms , 2003, BMVC.

[16]  Charlie David Frowd,et al.  EvoFIT: A Holistic, Evolutionary Facial Imaging System , 2002 .

[17]  Alice J. O'Toole,et al.  Low-dimensional representation of faces in higher dimensions of the face space , 1993 .

[18]  L Sirovich,et al.  Low-dimensional procedure for the characterization of human faces. , 1987, Journal of the Optical Society of America. A, Optics and image science.

[19]  J. W. Shepherd,et al.  An Interactive Computer System for Retrieving Faces , 1986 .

[20]  Lawrence Sirovich,et al.  Application of the Karhunen-Loeve Procedure for the Characterization of Human Faces , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Peter J. B. Hancock,et al.  An application of caricature: How to improve the recognition of facial composites , 2007 .

[22]  Nikolaus F. Troje,et al.  Representation of human faces , 2007 .

[23]  J. Elder,et al.  Towards Face Recognition at a Distance , 2006 .

[24]  Anil K. Jain,et al.  Soft Biometric Traits for Personal Recognition Systems , 2004, ICBA.

[25]  Peter J. B. Hancock,et al.  Testing Principal Component Representations for Faces , 1997, NCPW.

[26]  P. Jonathon Phillips,et al.  Face recognition vendor test 2002 , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[27]  Charlie D. Frowd,et al.  A forensically valid comparison of facial composite systems , 2005 .

[28]  Melanie Mitchell,et al.  An introduction to genetic algorithms , 1996 .

[29]  Mauro Barni,et al.  A new decoder for the optimum recovery of nonadditive watermarks , 2001, IEEE Trans. Image Process..

[30]  Minh N. Do,et al.  Wavelet-based texture retrieval using generalized Gaussian density and Kullback-Leibler distance , 2002, IEEE Trans. Image Process..

[31]  Charlie D. Frowd,et al.  Contemporary composite techniques: The impact of a forensically-relevant target delay. , 2005 .

[32]  S. Velastín,et al.  Fusion of Multiple Features for Identity Estimation , 2006 .

[33]  V. Bruce,et al.  Parallel approaches to composite production: interfaces that behave contrary to expectation , 2007, Ergonomics.

[34]  J. Tanaka,et al.  Features and their configuration in face recognition , 1997, Memory & cognition.

[35]  Hari Krishna Garg,et al.  Wavelet domain watermarking using maximum-likelihood detection , 2004, IS&T/SPIE Electronic Imaging.