Advertisement

Computational Analysis of Multiple Instance Learning-Based Systems for Automatic Visual Inspection: A Doctoral Research Proposal

  • Eduardo-José Villegas-JaramilloEmail author
  • Mauricio Orozco-Alzate
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 801)

Abstract

The objective of this proposal is to select and analyze, functionally and computationally, a set of algorithms used for the detection of defects by automatic visual inspection, which make use of multiple instance learning and have the potential to be improved. From the analyses, modifications or updates, it is proposed to speed-up the response of the automatic visual inspection systems, allowing thereby, a decrease of the amount of undetected defective products in the production lines.

Keywords

Algorithm complexity Classification algorithms MIL Visual inspection 

Notes

Acknowledgments

The authors acknowledge the support to attend DCAI’18 Doctoral Consortium provided by “Convocatoria para la Movilidad Internacional de la Universidad Nacional de Colombia (UNAL) 2016 - 2018”.

References

  1. 1.
    Brassard, G., Bratley, P.: Fundamentos de algoritmia. Prentice Hall, Montreal (1997)Google Scholar
  2. 2.
    Dietterich, T.G., Lathrop, R.H., Lozano-Pérez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artif. Intell. 89, 31–71 (1997)CrossRefGoogle Scholar
  3. 3.
    Du, R., Wu, Q., He, X., Yang, J.: MIL-SKDE: multiple-instance learning with supervised kernel density estimation. Signal Process. 93(6), 1471–1484 (2013)CrossRefGoogle Scholar
  4. 4.
    Faria, A., Coelho, F., Silva, A., Rocha, H., Almeida, G., Lemos, A., Braga, A.: MILKDE: a new approach for multiple instance learning based on positive instance selection and kernel density estimation. Eng. Appl. Artif. Intell. 59, 196–204 (2017)CrossRefGoogle Scholar
  5. 5.
    Fu, Z., Robles-Kelly, A., Zhou, J.: MILIS: multiple instance learning with instance selection. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 958–977 (2011)CrossRefGoogle Scholar
  6. 6.
    Gelder, V., Baase, S.: Algoritmos Computacionales - Introducción al análisis y diseño, 3rd edn. Pearson Educación, México (2002)Google Scholar
  7. 7.
    Herrera, F., Ventura, S., Bello, R., Cornelis, C., Zafra, A., Sánchez Tarragó, D., Vluymans, S.: Multiple Instance Learning - Foundations and Algorithms. Springer (2016)Google Scholar
  8. 8.
    Langone, R., Suykens, J.A.: Supervised aggregated feature learning for multiple instance classification. Inf. Sci. 375, 234–245 (2017)CrossRefGoogle Scholar
  9. 9.
    Malamas, E.N., Petrakis, E.G.M., Zervakis, M., Petit, L., Legat, J.D.: A survey on industrial vision systems, applications and tools. Image Vis. Comput. 21(2), 171–188 (2003)CrossRefGoogle Scholar
  10. 10.
    Mera, C., Orozco-Alzate, M., Branch, J., Mery, D.: Automatic visual inspection: an approach with multi-instance learning. Comput. Ind. 83, 46–54 (2016)CrossRefGoogle Scholar
  11. 11.
    Mera, C.A.: Detección de Defectos en Sistemas de Inspección Visual Automática a través del Aprendizaje de Múltiples Instancias. Ph.D. thesis, Universidad Nacional de Colombia (2017)Google Scholar
  12. 12.
    Tian, Y., Qi, Z., Ju, X., Shi, Y., Liu, X.: Nonparallel support vector machines for pattern classification. IEEE Trans. Cybern. 44(7), 1067–1079 (2013)CrossRefGoogle Scholar
  13. 13.
    Xiao, Y., Liu, B., Hao, Z., Cao, L.: A similarity-based classification framework for multiple-instance learning. IEEE Trans. Cybern. 44(4), 500–515 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Eduardo-José Villegas-Jaramillo
    • 1
    Email author
  • Mauricio Orozco-Alzate
    • 1
  1. 1.Facultad de Administración - Departamento de Informática y ComputaciónUniversidad Nacional de Colombia - Sede ManizalesManizalesColombia

Personalised recommendations