Meta-learning for Adaptive Image Segmentation

  • Aymen Sellaouti
  • Yasmina JaâfraEmail author
  • Atef Hamouda
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8814)


Most image segmentations require control parameters setting that depends on the variability of processed images characteristics. This paper introduces a meta-learning system using stacked generalization to adjust segmentation parameters within an object-based analysis of very high resolution urban satellite images. The starting point of our system is the construction of the knowledge database from the concatenation of images characterization and their correct segmentation parameters. Meta-knowledge database is then built from the integration of base-learners performance evaluated by cross-validation. It will allow knowledge transfer to second-level learning and the generation of the meta-classifier that will predict new image segmentation parameters. An experimental study on a satellite image covering the urban area of Strasbourg region enabled us to evaluate the effectiveness of the adopted approach.


Object-based analysis Segmentation Very high resolution satellite image Meta-learning Stacked generalization 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Blaschke, T.: Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing 65(1), 2–16 (2010)CrossRefGoogle Scholar
  2. 2.
    Cleve, C., Kelly, M., Kearns, F., Moritz, M.: Classification of the wildland urban interface: A comparison of pixel and object-based classifications using high-resolution aerial photography. Computers, Environment and Urban Systems 32(4), 317–326 (2008)CrossRefGoogle Scholar
  3. 3.
    Bhanu, B., Peng, J.: Adaptive integrated image segmentation and object recognition. IEEE Transactions on Systems Man and Cybernetics 30, 427–441 (2000)CrossRefGoogle Scholar
  4. 4.
    Bhanu, B., Lee, M., Ming, J.: Adaptive image segmentation using a genetic algorithm. IEEE Transactions on Systems, Man, and Cybernetics 25(12), 1543–1567 (1995)CrossRefGoogle Scholar
  5. 5.
    Derivaux, S., Lefevre, S., Wemmert, C., Korczak, J.: On machine learning in watershed segmentation. In: IEEE International Workshop on Machine Learning in Signal Processing (MLSP), pp. 187–192 (2007)Google Scholar
  6. 6.
    Wolpert, D.H., Macready, W.G.: No free lunch theorems for optimization. IEEE Transactions on Evolutionary Computation 1(1), 67–82 (1997)CrossRefGoogle Scholar
  7. 7.
    Vilalta, R., Drissi, Y.: A perspective view and survey of meta-learning. Artificial Intelligence Review 18(2), 77–95 (2002)CrossRefGoogle Scholar
  8. 8.
    Vincent, L., Soille, P.: Watersheds in digital spaces: An efficient algorithm based on immersion simulations. IEEE Pattern Recognition and Machine Intelligence 13(6), 583–598 (1991)CrossRefGoogle Scholar
  9. 9.
    Derivaux, S., Lefevre, S., Wemmert, C., Korczak, J.: Watershed Segmentation of Remotely Sensed Images Based on a Supervised Fuzzy Pixel Classification. In: Proceedings of the IEEE International Geosciences And Remote Sensing Symposium (IGARSS), pp. 3712–3715 (2006)Google Scholar
  10. 10.
    Attig, A., Perner, P.: A study on the case image description for learning the model of the watershed segmentation. Transactions on Case-Based Reasoning 2(1), 41–53 (2009)Google Scholar
  11. 11.
    Haralick, R.: Statistical and structural approaches to texture. Proceedings of the IEEE 67(5), 786–804 (1979)CrossRefGoogle Scholar
  12. 12.
    Sellaouti, A., Hamouda, A., Deruyver, A., Wemmert, C.: Hierarchical classification-based region growing (HCBRG): a collaborative approach for object segmentation and classification. In: Campilho, A., Kamel, M. (eds.) ICIAR 2012, Part I. LNCS, vol. 7324, pp. 51–60. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  13. 13.
    Kurtz, C., Passat, N., Ganarski, P., Puissant, A.: Extraction of complex patterns from multiresolution remote sensing images: A hierarchical top-down methodology. Pattern Recognition 45(2), 685–706 (2012)CrossRefGoogle Scholar
  14. 14.
    Wolpert, D.H.: Stacked generalization. Neural Networks 5(2), 241–259 (1992)MathSciNetCrossRefGoogle Scholar
  15. 15.
    Fan, D., Chan, P., Stolfo, S.: A comparative evaluation of combiner and stacked generalization. In: Proceedings of AAAI 1996 Workshop on Integrating Multiple Learned Models, pp. 40–46 (1996)Google Scholar
  16. 16.
    Seewald, A.: Towards Understanding Stacking: Studies of a General Ensemble Learning Scheme. The Vienna University of Technology (2003)Google Scholar
  17. 17.
    Skalak, D.: Prototype Selection for Composite Nearest Neighbor Classifiers. PhD thesis (1997)Google Scholar
  18. 18.
    Alpaydin, E.: Introduction to Machine Learning, 2nd edn. The MIT Press (2010)Google Scholar
  19. 19.
    Perlich, C., Swirszcz, G.: On cross-validation and stacking: building seemingly predictive models on random data. SIGKDD Explorations 12, 11–15 (2010)CrossRefGoogle Scholar
  20. 20.
    Brazdil, P., Soares, C., Costa, J.D.: Ranking learning algorithms: Using ibl and meta-learning on accuracy and time results. Machine Learning 50(3), 251–277 (2003)CrossRefzbMATHGoogle Scholar
  21. 21.
    Ting, K., Witten, I.: Issues in stacked generalization. Journal of Artificial Intelligence Research 10, 271–289 (1999)zbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Aymen Sellaouti
    • 1
    • 2
  • Yasmina Jaâfra
    • 1
    Email author
  • Atef Hamouda
    • 1
  1. 1.Faculté des Sciences de Tunis, LIPAHUniversité de Tunis El ManarTunisTunisia
  2. 2.LSIIT, Pôle APIUniversité de StrasbourgIllkirchFrance

Personalised recommendations