Global and Local Features for Char Image Classification

Part of the Lecture Notes in Computer Science book series (LNCS, volume 9107)

Abstract

The use of image analysis in understanding how powdered coal burns during the combustion plays a significant role in setting combustion parameters. During the pulverised coal combustion, char particles are produced by devolatising coal and represent the dominant stage in the combustion process. The pyrolysis produces different char morphologies that determine coal reactivity affecting the performance of coal combustion in power plants and the emissions of carbon dioxide, CO2. In this paper, an automatic char classification model is proposed using supervised learning. A general classification model is trained given a set of char particles classified by an expert. In particular, Support Vector Machine (SVM) and Random Forest are the trained classifiers. Two types of features are evaluated to built classification models: local and global. Local features are calculated using the Scale-Invariant Transform Feature (SIFT). Global features are defined based on the morphology classification by the International Committee for Coal and Organic Petrology (ICCP). Each classifier is trained by SVM or Random Forest and evaluated using a 10-fold cross-validation. The 70% of data is used as training set and the rest as testing set. A total of 2928 char-particle images are used for evaluating performance of classification models. Additionally, evaluation of model generalisation capability is done using a test set of 732 char particle images. Results showed that global features – defined by the application domain – increase significantly the accuracy of classifiers. Also, global features have more generalisation power than local features. Local features lack of meaning in the application domain and classifiers build with local features – such as SIFT – depend crucially on the training set.

Keywords

Char classification Global features Local features Bag-of-features Support Vector Machine Random Forest 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Alvarez, D., Lester, E.: Atlas of char occurrences. combustion working group, commission iii. In: Internacional Conference on Coal Petrology, ICCP (2001)Google Scholar
  2. 2.
    Alvarez, D., Borrego, A.G., Menéndez, R.: Unbiased methods for the morphological description of char structures. Fuel 76(13), 1241–1248 (1997)CrossRefGoogle Scholar
  3. 3.
    Avila, S., Thome, N., Cord, M., Valle, E., de Araujo, A.: Bossa: Extended bow formalism for image classification. In: 18th IEEE International Conference on Image Processing, ICIP (2011)Google Scholar
  4. 4.
    Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, COLT 1992 (1992)Google Scholar
  5. 5.
    Chaves, D., García, E., Trujillo, M., Barraza, J.M.: Char morphology from coal blends using images analysis. In: World Conference on Carbon, CARBON (2013)Google Scholar
  6. 6.
    Cloke, M., Lester, E.: Characterization of coals for combustion using petrographic analysis: A review. Fuel 73(3), 315–320 (1994)CrossRefGoogle Scholar
  7. 7.
    Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)MATHGoogle Scholar
  8. 8.
    Criminisi, A., Shotton, J., Konukoglu, E.: Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning. Foundations and Trends in Computer Graphics and Vision 7(2), 81–227 (2011)CrossRefMATHGoogle Scholar
  9. 9.
    Csurka, G., Bray, C., Dance, C., Fan, L.: Visual categorization with bags of keypoints. In: Workshop on Statistical Learning in Computer Vision, pp. 1–22 (2004)Google Scholar
  10. 10.
    Fan, R.E., Chang, K.W., Hsieh, C.J., Wang, X.R., Lin, C.J.: Liblinear: A library for large linear classification. Journal of Machine Learning Research 9, 1871–1874 (2008)MATHGoogle Scholar
  11. 11.
    Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR (2005)Google Scholar
  12. 12.
    Lowe, D.G.: Object recognition from local scale-invariant features. In: The Proceedings of the Seventh IEEE International Conference on Computer Vision, ICCV 1999 (1999)Google Scholar
  13. 13.
    Rojas, A.F., Burgos, J.M.B.: Caracterización morfológica del carbonizado de carbones pulverizados: estado del arte. Revista Facultad de Ingeniería Universidad de Antioquia (41), 84–97 (2007)Google Scholar
  14. 14.
    Rojas, A.F., Burgos, J.M.B.: Caracterización morfológica del carbonizado de carbones pulverizados: determinación experimental. Revista Facultad de Ingeniería Universidad de Antioquia (43), 42–58 (2008)Google Scholar
  15. 15.
    Tang, F., Lu, H., Sun, T., Jiang, X.: Efficient image classification using sparse coding and random forest. In: 5th International Congress on Image and Signal Processing, CISP (2012)Google Scholar
  16. 16.
    Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: IEEE Conference on Computer Vision and Pattern Recognition (2010)Google Scholar
  17. 17.
    Wu, T., Lester, E., Cloke, M.: Advanced automated char image analysis techniques. Energy & Fuels 20(3), 1211–1219 (2006)CrossRefGoogle Scholar
  18. 18.
    Yang, J., Yu, K., Gong, Y., Huang, T.: Linear spatial pyramid matching using sparse coding for image classification. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2009)Google Scholar
  19. 19.
    Yang, P., Yang, Y.H., Zhou, B.B., Zomaya, A.Y.: A review of ensemble methods in bioinformatics. Current Bioinformatics 5(4), 296–308 (2010)CrossRefGoogle Scholar
  20. 20.
    Zack, G.W., Rogers, W.E., Latt, S.A.: Automatic measurement of sister chromatid exchange frequency. J. Histochem. Cytochem. 25(7), 741–753 (1977)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Multimedia and Computer Vision GroupUniversidad del ValleCaliColombia
  2. 2.Coal Science and Technology GroupUniversidad del ValleCaliColombia

Personalised recommendations