Advertisement

Study on Machine Learning Algorithms to Automatically Identifying Body Type for Clothing Model Recommendation

  • Evandro Costa
  • Emanuele Silva
  • Hemilis Rocha
  • Artur Maia
  • Thales Vieira
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 747)

Abstract

The task of automatically identify body type with high accuracy is still a relevant problem in clothing fashion settings. This paper addresses such problem, presenting a study on machine learning techniques applied to classify women’s body shapes, taking into account a small set of body attributes, in order to further find appropriate clothing models. Thus, we perform a comparative study on such techniques to evaluate the accuracy of four classifiers, aiming at selecting the best of them to be used for clothing model recommendation based on rules. Overall, in the conducted computational experiment, Random Forest and SVM methods had the best performance, but the other two had also very good results, demonstrating their effectiveness to automatically identifying body type, serving as a relevant information to be used in our rule-based system to provide clothing model recommendation.

Keywords

Body type identification Machine learning Clothing model recommendation 

References

  1. 1.
    Adam, H., Galinksy, A.: Enclothed cognition. J. Exp. Soc. Psychol. 48(4), 918–925 (2012).  https://doi.org/10.1016/j.jesp.2012.02.008 CrossRefGoogle Scholar
  2. 2.
    Aguiar, T.: Personal Stylist: guia para consultores de imagem. Editora Senac São Paulo, São Paulo (2015)Google Scholar
  3. 3.
    Clarke, B., Fokoue, E., Zhang, H.: Principles and Theory for Data Mining and Machine Learning. Springer (2009).  https://doi.org/10.1007/978-0-387-98135-2
  4. 4.
    Cortes, C., Vapnik, V.: Support vector networks. Mach. Learn. 20(3), 273–297 (1995).  https://doi.org/10.1023/A:1022627411411 zbMATHGoogle Scholar
  5. 5.
    Quinlan, J.: Induction of decision trees. Mach. Learn. 1(1), 81–106 (1986).  https://doi.org/10.1007/BF00116251 Google Scholar
  6. 6.
    Patil, N., Lathi, R., Chitre, V.: Comparison of C5.0 & CART Classification algorithms using pruning technique. Int. J. Eng. Res. Technol. (IJERT) 1(4), June 2012, ISSN 2278-0181Google Scholar
  7. 7.
    Witten, I., Frank, E., Hall, M.: Data Mining: Practical Machine Learning Tools and Techniques, 3rd edn. Morgan Kaufmann Publishers Inc., San Francisco (2011)Google Scholar
  8. 8.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001).  https://doi.org/10.1023/A:1010933404324 CrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Evandro Costa
    • 1
  • Emanuele Silva
    • 1
  • Hemilis Rocha
    • 2
  • Artur Maia
    • 1
  • Thales Vieira
    • 3
  1. 1.Institute of ComputingFederal University of Alagoas - UFALMaceióBrazil
  2. 2.Informatics in Campus ViçosaFederal Institute of Alagoas - IFALMaceióBrazil
  3. 3.Institute of MathematicsFederal University of Alagoas - UFALMaceióBrazil

Personalised recommendations