Comparison of Combined Probabilistic Connectionist Models in a Forensic Application

  • Edmondo Trentin
  • Luca Lusnig
  • Fabio Cavalli
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7081)


A growing interest toward automatic, computer-based tools has been spreading among forensic scientists and anthropologists wishing to extend the armamentarium of traditional statistical analysis and classification techniques. The combination of multiple paradigms is often required in order to fit the difficult, real-world scenarios involved in the area. The paper presents a comparison of combination techniques that exploit neural networks having a probabilistic interpretation within a Bayesian framework, either as models of class-posterior probabilities or as class-conditional density functions. Experiments are reported on a severe sex determination task relying on 1400 scout-view CT-scan images of human crania. It is shown that connectionist probability estimates yield higher accuracies than traditional statistical algorithms. Furthermore, the performance benefits from proper mixtures of neural models, and it turns up affected by the specific combination technique adopted.


Multiple classifier neural net density estimation forensics 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)zbMATHGoogle Scholar
  2. 2.
    Brasili, P., Toselli, S., Facchini, F.: Methodological aspects of the diagnosis of sex based on cranial metric traits. Homo. 51, 68–80 (2000)Google Scholar
  3. 3.
    Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. Wiley, New York (1973)zbMATHGoogle Scholar
  4. 4.
    Haykin, S.: Neural Networks. A Comprehensive Foundation. Macmillan, New York (1994)zbMATHGoogle Scholar
  5. 5.
    Hsiao, T.H., Chang, H.P., Liu, K.M.: Sex determination by discriminant function analysis of lateral radiographic cephalometry. Journal of Forensic Sciences 41(5), 792 (1996)CrossRefGoogle Scholar
  6. 6.
    Nixon, M., Aguado, A.S.: Feature Extraction & Image Processing, 2nd edn. Academic Press (2008)Google Scholar
  7. 7.
    Novotny, V., Iscan, M., Loth, S.: Morphologic and osteometric assessment of age, sex, and race from the skull. In: Iscan, M.Y., Helmer, R.P. (eds.) Forensic Analysis of the Skull, pp. 71–88. Wiley-Liss, New York (1993)Google Scholar
  8. 8.
    Rsing, F.W., Graw, M., Marr, B., Ritz-Timme, S., Rothschild, M.A., Rzscher, K., Schmeling, A., Schrder, I., Geserick, G.: Recommendations for the forensic diagnosis of sex and age from skeletons. HOMO - Journal of Comparative Human Biology 58(1), 75–89 (2007)CrossRefGoogle Scholar
  9. 9.
    Trentin, E.: Networks with trainable amplitude of activation functions. Neural Networks 14(4-5), 471–493 (2001)CrossRefGoogle Scholar
  10. 10.
    Trentin, E.: Simple and Effective Connectionist Nonparametric Estimation of Probability Density Functions. In: Schwenker, F., Marinai, S. (eds.) ANNPR 2006. LNCS (LNAI), vol. 4087, pp. 1–10. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  11. 11.
    Walrath, D.E., Turner, P., Bruzek, J.: Reliability test of the visual assessment of cranial traits for sex determination. American Journal of Physical Anthropology 125(2), 132–137 (2004)CrossRefGoogle Scholar
  12. 12.
    Zhang, D., Lu, G.: A Comparative Study on Shape Retrieval Using Fourier Descriptors with Different Shape Signatures. Journal of Visual Communication and Image Representation 14(1), 41–60 (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Edmondo Trentin
    • 1
  • Luca Lusnig
    • 1
  • Fabio Cavalli
    • 2
  1. 1.Dip. di Ingegneria dell’InformazioneUniversità di SienaItaly
  2. 2.Research Unit of Paleoradiology and All. Sci.AOUTS TriesteItaly

Personalised recommendations