Abstract
EvoFIT, a computerized facial composite system is being developed as an alternative to current systems. EvoFIT faces are initially presented to a witness with random characteristics, but through a process of selection and breeding, a composite is "evolved." Comparing composites constructed with E-FIT, a current system, a naming rate of 10% was found for EvoFIT and 17% for E-FIT. Analysis revealed that target age was limiting factor for EvoFIT and a second study with age-appropriate targets visible during composite construction produced a naming rate similar to E-FIT. Two more-realistic studies were conducted that involved young target faces and two current systems (E-FIT and PROfit). Composites from both of these experiments were poorly named but a significant benefit emerged for EvoFIT.
- Acpo(S). 2000. National Working Practices in Facial Imaging. Association of Chief Police Officers (Scotland) Working Group.Google Scholar
- Bennett, P. 2000. The use of multiple composites in suspect identification. In Proceedings of the 3rd UK National Conference on Cranio-Facial Identification, Manchester, May 2000.Google Scholar
- Brace, N., Pike, G., and Kemp, R. 2000. Investigating E-FIT using famous faces. In Forensic Psychology and Law, A. Czerederecka, T. Jaskiewicz-Obydzinska, and J. Wojcikiewicz, Eds. Institute of Forensic Research Publishers, Krakow.Google Scholar
- Brown, G. D. A., Hulme, C., Hyland, P. D., and Mitchell, I. J. 1994. Cell suicide in the developing nervous systems: a functional neural network model. Cogn. Brain Res. 2, 71--75.Google ScholarCross Ref
- Bruce, V., Hanna, E., Dench, N., Healey, P., and Burton, M. 1992. The importance of "mass" in line-drawings of faces. Appl. Cogn. Psychol. 6, 619--628.Google ScholarCross Ref
- Bruce, V., Healey, P., Burton, A. M., Doyle, T., Coombes, A., and Linney, A. 1991. Recognising facial surfaces. Perception 20, 755--769.Google ScholarCross Ref
- Bruce, V., Ness, H., Hancock, P. J. B., Newman, C., and Rarity, J. 2002. Four heads are better than one. Combining face composites yields improvements in face likeness. J. Appl. Psychol. 87, 5, 894--902.Google ScholarCross Ref
- Brunelli, R. and Poggio, T. 1993. Face recognition: Features versus templates. IEEE Trans. PAMI 15, 10, 1042--1052. Google ScholarDigital Library
- Caldwell, C. and Johnston, V. S. 1991. Tracking a criminal suspect through "face-space" with a genetic algorithm. In Proceedings of the Fourth International Conference on Genetic Algorithms. Morgan Kaufmann Publishers, 416--421.Google Scholar
- Cootes, T. F., Walker, K. N., and Taylor, C. J. 2000. View-based active appearance models. In Proceedings of the International Conference on Face and Gesture Recognition. 227--232. Google Scholar
- Craw, I. and Cameron, P. 1991. Parameterising images for recognition and reconstruction. In Proceedings of the British Machine Vision Conference BMCV '91. Turing Institute Press and Springer Verlag.Google Scholar
- Davies, G., Milne, A., and Shepherd, J. 1983. Searching for operator skills in face composite reproduction. J. Police Sci. Adm. 11, 4, 405--409.Google Scholar
- Davies, G. M. and Oldman, H. 1999. The impact of character attribution on composite production: A real world effect? Curr. Psychol. Dev. Learn. Pers. Social 18, 1, 128--139.Google ScholarCross Ref
- Davies, G. M., van der Willik, P., and Morrison, L. J. 2000. Facial composite production: A comparison of mechanical and computer-driven systems. J. Appl. Psychol. 85, 1, 119--124.Google ScholarCross Ref
- Fic. 1999. Crime Management Division: Facial Imaging Course. Scottish Police College.Google Scholar
- Frowd, C. D. 2001. EvoFIT: A Holistic, Evolutionary Facial Imaging System. Unpublished Ph.D. Thesis, University of Stirling, Stirling, UK.Google Scholar
- Gibling, F. and Bennett, P. 1994. Artistic enhancement in the production of photofit likeness: An examination of its effectiveness in leading to suspect identification. Psychol. Crime Law 1, 93--100.Google ScholarCross Ref
- Green, D. L. and Geiselman, R. E. 1989. Building composite facial images: Effects of feature saliency and delay of construction. J. Appl. Psychol. 74, 714--721.Google ScholarCross Ref
- Hancock, P. J. B. 2000. Evolving faces from principal components. Behav. Res. Methods Instrum. Comput. 32, 2, 327--333.Google ScholarCross Ref
- Hancock, P. J. B., Bruce, V., and Burton, A. M. 1997. Testing principal component representations for faces. In Proceedings of 4th Neural Computation and Psychology Workshop, J. A. Bullinaria, D. W. Glasspool, and G. Houghton, Eds. Springer-Verlag, London, 84--97.Google Scholar
- Hancock, P. J. B., Bruce, V., and Burton, A. M. 1998. A comparison of two computer-based face recognition systems with human perceptions of faces. Vis. Res. 38, 2277--2288.Google ScholarCross Ref
- Hancock, P. J. B., Bruce, V., and Burton, A. M. 2000. Recognition of unfamiliar faces. Trends Cogn. Sci. 4, 9, 330--337.Google ScholarCross Ref
- Hancock, P. J. B., Burton, A. M., and Bruce, V. 1996. Face processing: Human perception and principal components analysis. Mem. Cognit. 24, 26--40.Google ScholarCross Ref
- Kovera, M. B., Penrod, S. D., Pappas, C., and Thill, D. L. 1997. Identification of computer generated facial composites. J. Appl. Psychol. 82, 2, 235--246.Google ScholarCross Ref
- Le Cun, Y., Denker, J. S., and Solla, S. A. 1990. Optimal brain damage. Adv. Neural Inf. Syst. 2, 598--605. Google Scholar
- Light, L. L., Kayra-Stuart, F., and Hollander, S., 1979. Recognition memory for typical and unusual faces. J. Exp. Psychol. Hum. Learn. Mem. 5, 3, 212--228.Google ScholarCross Ref
- McNeil, J. E., Wray, J. L., Hibler, N. S., Foster, W. D., Rhyne, C. E., and Thibault, R. 1987. Hypnosis and Identi-kit: A study to determine the effect of using hypnosis in conjunction with the making of identikit composites. J. Police Sci. Adm. 15, 63--67.Google Scholar
- O'Toole, A. J., Vetter, T., Volz, H., and Salter, E. M. 1997. Three-dimensional caricatures of human heads: Distinctiveness and the perception of facial age. Perception 25, 719--732.Google ScholarCross Ref
- Rakover, S. S. and Cahlon, B. 1996. To catch a thief with a recognition test: The model and some empirical results. Cogn. Psychol. 21, 423--468.Google ScholarCross Ref
- Shapiro, P. N. and Penrod, S. D. 1986. Meta-analysis of facial identification rates. Psychol. Bull. 100, 139--156.Google ScholarCross Ref
- Sirovich, L. and Kirby, M. 1987. Low-dimensional procedure for the characterization of human faces. J. Opt. Soc. Amer. A 4, 519--524.Google ScholarCross Ref
- Troje, N. F. and Vetter, T. 1996. Representation of Human Faces. Tech. rep., Max-Planck-Institute, Tubingen, Germany.Google Scholar
- Valentine, T. and Endo, M. 1992. Towards an exemplar model of face processing: the effects of race and distinctiveness. Q. J. Exp. Psychol. A 44, 671--703.Google ScholarCross Ref
Index Terms
- EvoFIT: A holistic, evolutionary facial imaging technique for creating composites
Recommendations
Catching Even More Offenders with EvoFIT Facial Composites
EST '12: Proceedings of the 2012 Third International Conference on Emerging Security TechnologiesFacial composites are an investigative tool used by police to identify suspects of crime. Unfortunately, traditional methods to construct the face have rather low success rates. We have been developing a new recognition-based method called EvoFIT that ...
Conference report: the fifth ACM conference on electronic commerce
This report summarizes events and activities at the Fifth Association for Computing Machinery (ACM) Conference on Electronic Commerce (EC'04), held May 17-20 2004 in New York City. The program featured twenty-four talks, twenty-one brief announcements, ...
Design optimization of 3D reinforced concrete structures having shear walls
This paper presents a computer-based method for the optimal design of three-dimensional Reinforced Concrete (RC) structures having beams subjected to shear force and bending moment, columns subjected to biaxial moments, biaxial shears and axial loads, ...
Comments