Evaluation of Sex Identification of Unidentified Persons through Facial X-rays Using Machine Learning Methods

• Thais Mayumi Oshiro USP
• Suzana Papile Maciel Carvalho USP
• Arsenio Sales Peres USP
• Renato Tinós USP
• Ricardo Henrique Alves da Silva USP
• José Augusto Baranauskas USP

Abstract

Identification corresponds to the set of different procedures to identify a person or object. The process of identifying individuals by manual radiographic comparison appears to be very slow requiring high skills and accuracy by the human expert. Applying computer systems to assist the identification can improve this process, making it faster and more practical. Therefore, using measurements obtained from human frontal sinus radiographs this study aims to use Machine Learning methods and techniques to evaluate if it is possible to establish patterns among genders, thereby assisting in the identification process, using proposed measures from specific literature. Our results indicate the proposed measures are more indicated for specialization rather than generalization.

References

Batista, G. E. A. P. A., Prati, R. C., and Monard, M. C. (2004). A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explorations, 6(1):20–29.

Bishop, C. M. (2006). Pattern Recognition and Machine Learning.

Camargo, J. R. (2000). Estimativa do sexo através das características radiográficas dos seios frontais. Technical report, Universidade Estadual de Campinas, Piracicaba.

Demsar, J. (2006). Statistical comparison of classifiers over multiple data sets. Journal of Machine Learning Research, 7:1–30.

Domingos, P. (1999). The role of occam’s razor in knowledge discovery. Data Mining and Knowledge Discovery, 3:409–25.

Hastie, T., Tibshirani, R., and Friedman, J. (2001). The elements of statistical learning, data mining, inference and prediction. Springer, Berlin.

Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In IJCAI, pages 1137–1145.

Lee, H. D., Monard, M. C., and Baranauskas, J. A. (2000). A practical approach for knowledge-driven constructive induction. Argentine Symposium on Artificial Intelligence, pages 71–85.

Mitchell, T. M. (1997). Machine Learning. McGraw–Hill.

Monard, M. C. and Baranauskas, J. A. (2003). Conceitos sobre Aprendizado de Máquina, chapter 4, pages 89–114. In [Rezende 2003].

Nassar, D. E. M. and Ammar, H. H. (2007). A neural network system for matching dental radiographs. Pattern Recognition, 40(1):65–79.

Oliveira, R. N., Daruge, E., Galvão, L. C. C., and Tumang, A. J. (1998). Contribuição da odontologia legal para a identificação post-mortem. 55(2):117–122.

Rezende, S. O., editor (2003). Sistemas Inteligentes. Manole.

Ribeiro, F. A. Q. (1993). Um método de padronização de medidas feitas em radiografias dos seios frontais para ser utilizado na identificação pessoal. Technical report, Universidade Federal de São Paulo, UNIFESP, São Paulo.

Sweet, D. (2001). Why a dentist for identification? Dent Clin North Am, 45(2):237–51.

Vanrell, J. P. (2002). Odontologia legal e antropologia forense. Guanabara Koogan, Rio de Janeiro, 1 edition.

Witten, I. H. and Frank, E. (2005). Data Mining: Practical Machine Learning Tools and Techniques, Second Edition. Morgan Kaufmann.