Advertisement

Pattern Detection in Images Using LBP-Based Relational Operators

  • José María Molina-Casado
  • Enrique J. Carmona
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7931)

Abstract

This paper describes two new pattern detection image operators, \(\Re_{1}^{riu2}\) and \(\Re_{2}\), called, in a generic way, LBP-based relational operators (LBP-RO). The former is rotational invariant and allows searching for a particular pattern disposes in any direction, the later is a binary operator designed to find image patterns that can be modeled by a pattern function. Both of them are invariants against any monotonic transformation of the image gray scale. We have applied these operators in a case study dedicated to segment the ONH in eye fundus color photographic images. The new segmentation method, called GA+LBP-RO, was compared to a competitive ONH segmentation method in the literature and the results obtained by our method proved to be equal to or better.

Keywords

Local Binary Pattern (LBP) Relational Operator Genetic Algorithm ONH Segmentation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    DRIONS-DB: Digital retinal images for optic nerve segmentation database (January 2013), http://www.ia.uned.es/personal/ejcarmona/DRIONS-DB.html
  2. 2.
    ONHSD: Optic nerve head segmentation dataset (January 2013), http://reviewdb.lincoln.ac.uk/Image%20Datasets/ONHSD.aspx
  3. 3.
    Carmona, E.J., Rincón, M., García-Feijoo, J., Martínez-de-la Casa, J.M.: Identification of the optic nerve head with genetic algorithms. Artificial Intelligence in Medicine 43, 243–259 (2008)CrossRefGoogle Scholar
  4. 4.
    Lowell, J., Hunter, A., Steel, D., Basu, A., Ryder, R., Fletcher, E.: Optic nerve head segmentation. IEEE Transaction on Medical Imaging 23(2), 256–264 (2004)CrossRefGoogle Scholar
  5. 5.
    Molina, J.M., Carmona, E.J.: Localization and segmentation of the optic nerve head in eye fundus images using pyramid representation and genetic algorithms. In: Ferrández, J.M., Álvarez Sánchez, J.R., de la Paz, F., Toledo, F.J. (eds.) IWINAC 2011, Part I. LNCS, vol. 6686, pp. 431–440. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  6. 6.
    Ojala, T., Pietikäinen, M., Harwood, D.: A comparative study of texture measures with classification based on featured distributions. Pattern Recognition 29, 51–59 (1996)CrossRefGoogle Scholar
  7. 7.
    Ojala, T., Pietikäinen, M., Mäenpää, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence 24, 971–987 (2002)CrossRefGoogle Scholar
  8. 8.
    Setia, L., Teynor, A., Halawani, A., Burkhardt, H.: Grayscale medical image annotation using local relational features. Pattern Recognition Letters 29, 2039–2045 (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • José María Molina-Casado
    • 1
  • Enrique J. Carmona
    • 1
  1. 1.Dpto. de Inteligencia Artificial, ETSI InformáticaUniversidad Nacional de Educación a Distancia (UNED)MadridSpain

Personalised recommendations