Advertisement

Building the “Automatic Body Condition Assessment System” (ABiCA), an Automatic Body Condition Scoring System using Active Shape Models and Machine Learning

  • Rafael Tedín
  • José A. Becerra
  • Richard J. Duro
Chapter
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 234)

Abstract

A step by step reconstruction of the process that has been followed for building the Automatic Body Condition Assessment (ABiCA) system is presented. ABiCA is an automatic body condition scoring system for dairy cattle using images taken using hand-held cameras. The problem is decomposed into two sub-problems that are solved separately. Firstly, the shape of a cow is found and then the body condition score is estimated using this shape. The solutions to those problems are then combined to build the system. The shape of a cow is found using Active Shape Model (ASMs) tuned with an evolutionary algorithm. The shape feeds then a symbolic regression function evolved by means of genetic programming to finally estimate the body condition score of the cow. The error of the ABiCA system is reasonable, given the uncertainties of the expert’s scores. There is nevertheless room for improvement since it has been observed that some images might be too difficult for the system. Methods on how to automatically discard those images are being investigated.

Keywords

Active Shape Model Body Condition Score Evolutionary Algorithm Genetic Programming Machine Learning 

References

  1. 1.
    Bewley, J.M., Schutz, M.M.: An interdisciplinary review of body condition scoring for dairy cattle. Prof. Anim. Sci. 24, 507–529 (2008)Google Scholar
  2. 2.
    Cootes, T.F., Taylor, C.J.: Active shape models—‘smart snakes’. In: Proceedings of the British Machine Vision Conference, Springer-Verlag, pp. 266–275 (1992)Google Scholar
  3. 3.
    Upham, G.: The use of body condition scores in grouping of lactating cows. Compend. Continuing Educ. Pract. Vet. 12, 581–589 (1990)Google Scholar
  4. 4.
    Leroy, T., Aerts, J.M., Eeman, J., Maltz, E., Stojanovski, G., Berckmans, D.: Automatic Determination of Body Condition Score of Cows Based on 2D Images. Wageningen Academic Publishers, Netherlands (2005)Google Scholar
  5. 5.
    Coffey, M.P., Simm, G., Hill, W.G., Brotherstone, S.: Genetic evaluations of dairy bulls for daughter energy balance profiles using linear type scores and body condition score analyzed using random regression. J. Dairy Sci. 86, 2205–2212 (2003)CrossRefGoogle Scholar
  6. 6.
    Ferguson, J.D., Azzaro, G., Licitra, G.: Body condition assessment using digital images. J. Dairy Sci. 89, 3833–3841 (2006)CrossRefGoogle Scholar
  7. 7.
    Bewley, J.M., Peacock, A.M., Lewis, O., Boyce, R.E., Roberts, D.J., Coffey, M.P., Kenyon, S.J., Schutz, M.M.: Potential for estimation of body condition scores in dairy cattle from digital images. J. Dairy Sci. 91, 3439–3453 (2008)CrossRefGoogle Scholar
  8. 8.
    Halachmi, I., Polak, P., Roberts, D.J., Klopcic, M.: Cow body shape and automation of condition scoring. J. Dairy Sci. 91(11), 4444–4451 (2008)Google Scholar
  9. 9.
    Azzaro, G., Caccamo, M., Ferguson, J., Battiato, S., Farinella, G., Guarnera, G., Puglisi, G., Petriglieri, R., Licitra, G.: Objective estimation of body condition score by modeling cow body shape from digital images. J. Dairy Sci. 94(4), 2126–2137 (2011)CrossRefGoogle Scholar
  10. 10.
    Cootes, T.F., Taylor, C.J.: Using grey-level models to improve active shape model search. In: Pattern Recognition, 1994. Vol. 1—Conference A: Computer Vision & Image Processing., Proceedings of the 12th IAPR International Conference on. vol 1. pp. 63–67 (1994)Google Scholar
  11. 11.
    Tedín, R., Becerra, J.A., Duro, R.J.: Using classifiers as heuristics to describe local structure in active shape models with small training sets. Pattern Recogn. Lett. 34, 1710–1718 (2013). doi: 10.1016/j.patrec.2013.04.026
  12. 12.
    Wang, Y., Witten, I.H.: Inducing model trees for continuous classes. In: Proceedings of the 9th European Conference on Machine Learning Poster Papers, pp. 128–137 (1997)Google Scholar
  13. 13.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. SIGKDD Explor. Newsl. 11(1), 10–18 (2009)CrossRefGoogle Scholar
  14. 14.
    Koschan, A., Kang, S., Paik, J., Abidi, B., Abidi, M.: Color active shape models for tracking non-rigid objects. Pattern Recogn. Lett. 24(11), 1751–1765 (2003)CrossRefGoogle Scholar
  15. 15.
    Viola, P., Jones, M.: Robust real-time object detection. Int. J. Comput. Vision 57(2), 137–154 (2002)CrossRefGoogle Scholar
  16. 16.
    Koza, J.R.: Genetic Programming: On the Programming of computers by Means of Natural Selection. MIT Press, Cambridge (1992)Google Scholar
  17. 17.
    Storn, R., Price, K.V.: Differential evolution—a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim. 11, 341–359 (1997)MathSciNetCrossRefMATHGoogle Scholar
  18. 18.
    Caamaño, P., Bellas, F., Becerra, J.A., Duro, R.J.: Application domain study of evolutionary algorithms in optimization problems. In: Proceedings of the GECCO 2008, pp. 377–384 (2008)Google Scholar
  19. 19.
    Caamaño, P., Tedín, R., Paz-Lopez, A., Becerra, J.A.: Jeaf: A java evolutionary algorithm framework. In: IEEE Congress on Evolutionary Computation, IEEE, pp. 1–8 (2010)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Rafael Tedín
    • 1
  • José A. Becerra
    • 1
  • Richard J. Duro
    • 1
  1. 1.Integrated Group for Engineering ResearchUniversity of A CoruñaFerrolSpain

Personalised recommendations