Evolutionary Image Registration in Craniofacial Superimposition: Modeling and Incorporating Expert Knowledge
Abstract
Craniofacial superimposition involves the process of overlaying a skull with a number of ante-mortem images of an individual and the analysis of their morphological correspondence. This research focused on the skull-face overlay stage with the aim of modeling the expert knowledge that is related to the existing anthropometric differences among landmarks and incorporating it into this stage. Consequently, we have moved from a single-objective optimization problem to a multiobjective optimization one aimed to reduce the distances between pairs of landmarks from each group independently. To tackle it, two classic approaches from the area of multicriteria decision making were used: weighted sum and lexicographical order. The results, which were obtained over a Ground Truth dataset, are promising in those cases where the forensic expert has located a large number of landmarks, and worse results than the state of the art method in cases with few landmarks.
Notes
Acknowledgments
This research was supported by the Spanish Ministerio de Economía y Competividad under NEWSOCO project TIN2015-67661-P, and the Andalusian Dept. of Innovación, Ciencia y Empresa under project TIC2011-7745, including European Development Regional Funds (EDRF). Mr. O. Gomez’s work was supported by Spanish MECD FPU grant FPU14/02380. Dr. Ibañez’s work was supported by Spanish MINECO Juan de la Cierva Fellowship JCI-2012-15359.
References
- 1.Yoshino, M.: Craniofacial superimposition. In: Wilkinson, C., Rynn, C. (eds.) Craniofacial Identification, pp. 238–253. Cambridge University Press, Cambridge (2012)CrossRefGoogle Scholar
- 2.Damas, S., Cordón, O., Ibáñez, O., Santamaría, J., Alemán, I., Botella, M.: Forensic identification by computer-aided craniofacial superimposition: a survey. ACM Comput. Surv. 43, 27 (2011)CrossRefGoogle Scholar
- 3.Damas, S., Wilkinson, C., Kahana, T., Veselovskaya, E., Abramov, A., Jankauskas, R., Jayaprakash, P.T., Ruiz, E., Navarro, F., Huete, M.I., Cunha, E., Cavalli, F., Clement, J., Lestón, P., Molinero, F., Briers, T., Viegas, F., Imaizumi, K., Humpire, D., Ibáñez, O.: Study on the performance of different craniofacial superimposition approaches (II): best practices proposal. Forensic Sci. Int. 257, 504–508 (2015)CrossRefGoogle Scholar
- 4.Zitovà, B., Flusser, J.: Image registration methods: a survey. Image Vis. Comput. 21, 977–1000 (2003)CrossRefGoogle Scholar
- 5.Damas, S., Cordón, O., Santamaría, J.: Medical image registration using evolutionary computation: an experimental study. IEEE Comput. Intell. Mag. 6, 26–42 (2011)CrossRefGoogle Scholar
- 6.Chankong, V., Haimes, Y.: Multiobjective Decision Making Theory and Methodology. North-Holland, Amsterdam (1983)MATHGoogle Scholar
- 7.Campomanes-Alvarez, B., Ibanez, O., Campomanes-Alvarez, C., Damas, S., Cordon, O.: Modeling facial soft tissue thickness for automatic skull-face overlay. IEEE Trans. Inf. Forensics Secur. PP(99), 1 (2015)Google Scholar
- 8.Ibáñez, O., Cavalli, F., Campomanes-Álvarez, B.R., Campomanes-Álvarez, C., Valsecchi, A., Huete, M.I.: Ground truth data generation for skull-face overlay. Int. J. Leg. Med. 129, 569–581 (2015)CrossRefGoogle Scholar
- 9.Huete, M.I., Ibáñez, O., Wilkinson, C., Kahana, T.: Past, present, and future of craniofacial superimposition: literature and international surveys. Leg. Med. 17(4), 267–278 (2015)CrossRefGoogle Scholar
- 10.Ghosh, A.K., Sinha, P.: An economised craniofacial identification system. Forensic Sci. Int. 117, 109–119 (2001)CrossRefGoogle Scholar
- 11.Nickerson, B.A., Fitzhorn, P.A., Koch, S.K., Charney, M.: A methodology for near-optimal computational superimposition of two-dimensional digital facial photographs and three-dimensional cranial surface meshes. J. Forensic Sci. 36, 480–500 (1991)CrossRefGoogle Scholar
- 12.Ibáñez, O., Ballerini, L., Cordón, O., Damas, S., Santamaría, J.: An experimental study on the applicability of evolutionary algorithms to craniofacial superimposition in forensic identification. Inf. Sci. 79, 3998–4028 (2009)CrossRefGoogle Scholar
- 13.Ibáñez, O., Cordón, O., Damas, S., Santamaría, J.: Modeling the skull-face overlay uncertainty using fuzzy sets. IEEE Trans. Fuzzy Syst. 16, 946–959 (2011)Google Scholar
- 14.Ibáñez, O., Cordón, O., Damas, S.: A cooperative coevolutionary approach dealing with the skull face overlay uncertainty in forensic identification by craniofacial superimposition. Soft Comput. 18, 797–808 (2012)CrossRefGoogle Scholar
- 15.Faugeras, O.: Three-Dimensional Computer Vision. A Geometric Viewpoint, 1st edn. The MIT Press, Cambridge (1993)Google Scholar
- 16.Cummaudo, M., Guerzoni, M., Marasciuolo, L., Gibelli, D., Cigada, A., Obertová, Z., Ratnayake, M., Poppa, P., Gabriel, P., Ritz-Timme, S., Cattaneo, C.: Pitfalls at the root of facial assessment on photographs: a quantitative study of accuracy in positioning facial landmarks. Int J. Leg. Med. 127, 699–706 (2013)CrossRefGoogle Scholar
- 17.Bookstein, F.L.: Morphometric Tools for Landmark Data: Geometry and Biology, 1st edn. Cambridge University Press, New York (1991)MATHGoogle Scholar
- 18.Krasnogor, N., Smith, J.: A tutorial for competent memetic algorithms: model, taxonomy, and design issues. IEEE Trans. Evol. Comput. 9(5), 474–488 (2005)CrossRefGoogle Scholar