Improved Recognition of Spectrally Mixed Land Cover Classes Using Spatial Textures and Voting Classifications

  • Jonathan C.W. Chan
  • Ruth S. DeFries
  • John R. G. Townshend
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2124)


Regenerating forest is important to account for carbon sink. Mapping regenerating forest from satellite data is difficult because it is spectrally mixed with natural forest. This paper investigated the combined use of texture features and voting classifications to enhance recognition of these two classes. Bagging and boosting were applied on Learning Vector Quantization (LVQ) and decision tree. Our results show that spatial textures improved separability. After applying voting classifications, class accuracy of decision tree increased by 5–7% and that of LVQ by approximately 3%. Substantial reduction (between 23% to 40%) of confusions between regenerating forest and natural forest were recorded. Comparatively, bagging is more consistent than boosting. An interesting observation is that even LVQ, a stable learner, was able to benefit from both voting classification algorithms.


pattern recognition spatial textures rating classifier 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Haralick, R.M.: Statistical and Structural Approaches to Texture. Proc. IEEE, 67 (1979) 786–803CrossRefGoogle Scholar
  2. 2.
    Breiman, L.: Bagging Predictors. Machine Learning, 24 (1996) 23–140MathSciNetGoogle Scholar
  3. 3.
    Kohonen, T.: Self-Organizing Maps. Springer-Verlag, Berlin (1995)Google Scholar
  4. 4.
    Intergovernmental Panel on Climate Change: Land Use, Land-Use Change, and Forestry. A Special Report of IPCC, Summary for Policymakers (2000)Google Scholar
  5. 5.
    Houghton, R.A., Boone, R.D., Fruci, J.R., Hobbie, J.E., Melillo, J.M., Palm, C.A., Peterson, B.J., Shaver, G.R., Woodwell, G.M., Moore, B., Skole, D.L., Meyers, N.: The Flux of Carbon from Terrestrial Ecosystems to the Atmosphere in 1980 due to Changes in Land Use: Geographic Distribution of the Global Flux. Tellus, 39B (1987) 122–139CrossRefGoogle Scholar
  6. 6.
    Lugo, A.E., Brown, S.: Tropical Forests as Sinks of Atmospheric Carbon. Forest Ecology and Management, 54 (1992) 239–255CrossRefGoogle Scholar
  7. 7.
    Lucas, R.M., Honzak, M., Curran, P.J., Foody, G.M., Nguele, D.T.: Characterizing Tropical Forest Regeneration in Cameroon Using NOAA AVHRR Data. Int. J. Remote Sensing, 21 (2000) 2831–2854CrossRefGoogle Scholar
  8. 8.
    Richards, T., Gallego, J., Achard, F.: Sampling for Forest Cover Change Assessment at the Pan-Tropical Scale. Int. J. Remote Sensing, 21 (2000) 1473–1490CrossRefGoogle Scholar
  9. 9.
    Laporte, N., Justice, C., Kendall, J.: Mapping the Dense Humid Forest of Cameroon and Zaire Using AVHRR Satellite Data. Int. J. Remote Sensing, 16 (1995) 1127–1145CrossRefGoogle Scholar
  10. 10.
    Lucas, R.M., Honzak, M., Curran, P.J., Foody, G.M., Milne, R., Brown, T., Amaral, S.: Mapping the Regional Extent of Tropical Forest Regeneration Stages in the Brazilian Legal Amazon Using NOAA AVHRR Data. Int. J. Remote Sensing, 21 (2000) 2855–2881CrossRefGoogle Scholar
  11. 11.
    Townshend, J.R.G., Justice, C.O.: Spatial Variability of Images and the Monitoring of Changes in the Normalized Difference Vegetation Index. Int. J. Remote Sensing, 16 (1995) 2187–2196CrossRefGoogle Scholar
  12. 12.
    Mather, P.M., Tso, B.C.K., Koch, M.: An Evaluation of Landsat TM Spectral Data and SAR-Derived Textural Information for Lithological Discrimination in the Red Sea Hills, Sudan. Int. J. Remote Sensing, 19 (1998) 587–604CrossRefGoogle Scholar
  13. 13.
    Bruzzone, L., Conese, C., Maselli, F., Roli, F.: Multi-Source Classification of Complex Rural Areas by Statistical and Neural-Network Approaches. Photogram. Eng. & Remote Sensing, 63 (1997) 523–533Google Scholar
  14. 14.
    Smits, P.C., Annoni, A.: Updating Land-cover Maps by Using Texture Information From Very High-resolution Space-borne Imagery. IEEE Trans. Geosci. Remote Sensing, 37 (1999) 1244–1254CrossRefGoogle Scholar
  15. 15.
    He, D.C., Wang, L.: Texture Unit, Texture Spectrum, and Texture Analysis. IEEE Trans. Geosci. Remote Sensing, 28 (1990) 509–512CrossRefGoogle Scholar
  16. 16.
    Maclin, R., Opitz, D.: An Empirical Evaluation of Bagging and Boosting. In: Proc. of the 14th Nat. Conf. on Artificial Intelligence, 27–31 July, Providence, Rhode Island, AAAI Press (1997) 546–551Google Scholar
  17. 17.
    Quinlan, R.J.: Bagging, Boosting, and C4.5. In: Proc. of the Thirteenth Nat. Conference on Artificial Intelligence. Cambridge, MA. AAAI Press/MIT Press (1996) 725–730Google Scholar
  18. 18.
    Breiman, L.: Arcing classifiers. Technical Report, Statistics Department, University of California at Berkeley (1996)Google Scholar
  19. 19.
    Freund, Y., Schapire, R.E.: Experiments with a New Boosting Algorithm. Machine Learning: Proc. of the 13th International Conference, 3–6 July, Bari (1996) 148–156Google Scholar
  20. 20.
    Bauer, E., Kohavi, R.: An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants. Machine Learning, 36 (1998) 105–139CrossRefGoogle Scholar
  21. 21.
    Chan, J.C.W., Huang, C., DeFries, R.S.: Enhanced Algorithm Performance for Land Cover Classification from Remotely Sensed Data Using Bagging and Boosting. IEEE Trans. Geosc. Remote Sensing, 39 (2001) 693–695CrossRefGoogle Scholar
  22. 22.
    Chan, J.C.W., Chan, K.P., Yeh, A.G.O.: Detecting the Nature of Change in an Urban Environment-A Comparison of Machine Learning Algorithms. Photo. Eng. & Remote Sensing, 67 (2001) 213–225Google Scholar
  23. 23.
    Friedman, J.H.: On Bias, Variance, 0/1-loss, and the Curse-of-Dimensionality. Data Mining and Knowledge Discovery, 1 (1997) 55–77CrossRefGoogle Scholar
  24. 24.
    Quinlan, R.J.: C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, Inc., San Mateo, California (1993)Google Scholar
  25. 25.
    Riou, R., Seyler, F.: Texture Analysis of Tropical Rain Forest Infrared Satellite Images. Photogramm. Engineering and Remote Sensing, 63 (1997) 515–521Google Scholar
  26. 26.
    Kohavi, R., Sommerfield, D., Dougherty, J.: Data mining using MLC++: a machine learning library in C++, Tools with Artificial Intelligence, IEEE Computer Society Press (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  • Jonathan C.W. Chan
    • 1
  • Ruth S. DeFries
    • 2
  • John R. G. Townshend
    • 1
  1. 1.Laboratory for Global Remote Sensing Studies Geography DepartmentUniversity of MarylandCollege ParkUSA
  2. 2.Earth System Interdisciplinary Science Center and Geography DepartmentUniversity of MarylandCollege ParkUSA

Personalised recommendations