Digital Image Processing for Spatial Object Recognition via Integration of Nonlinear Wavelet-Based Denoising and Clustering-Based Segmentation

  • Zhengmao Ye
  • Habib Mohamadian
Conference paper
Part of the Lecture Notes in Geoinformation and Cartography book series (LNGC)


Spatial digital image analysis plays an important role in information decision support systems, especially for regions frequently affected by hurricanes and tropical storms. For aerial and satellite imaging based pattern recognition, it is unavoidable for these images to be affected by various uncertainties, such as atmospheric medium dispersion. Image denoising is thus necessary to remove noise and retain important digital image signatures. The linear denoising approach is suitable for slow variation noise cases. However, the spatial object recognition problem is essentially nonlinear. Being a nonlinear wavelet based technique, wavelet decomposition is effective for denoising blurred spatial images. The digital image is split into four subbands, representing approximation and three details (high frequency features) in the horizontal, vertical and diagonal directions. The proposed soft thresholding wavelet decomposition is simple and efficient for noise reduction. To further identify the individual targets, a nonlinear K-means clustering based segmentation approach is proposed for image object recognition. Selected spatial images were taken across hurricane affected Louisiana areas. In addition for the evaluation of this integration approach via qualitative observation, quantitative measures are proposed on the basis of information theory. Discrete entropy, discrete energy and mutual information are applied for accurate decision support.


Mutual Information Image Segmentation Gray Level Cluster Center Wavelet Coefficient 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. Duda et al. (2000) Pattern classification, 2nd edn. Wiley, ISBN: 978-0-471-05669-0, Hoboken, New Jersey, USAGoogle Scholar
  2. Ghazel M, Freeman G, Vrscay E (2006) Fractal-wavelet image denoising revisited. IEEE Trans Image Process 15:9CrossRefGoogle Scholar
  3. Gonzalez R, Woods R (2007) Digital image processing, 3rd edn. Prentice Hall, ISBN-13: 9780131687288, Upper Saddle River, New Jersey, USAGoogle Scholar
  4. Haykin S (1999) Neural networks: a comprehensive foundation, 2nd edn. Prentice Hall, ISBN-13: 9780131471399, Upper Saddle River, New Jersey, USAGoogle Scholar
  5. Jaffar M, Naveed N, Ahmed B, Hussain A, Mirza A (2009) Fuzzy C-means clustering with spatial information for color image segmentation. In: Proceedings of the 2009 international conference on electrical engineering, Lahore, 9–11 April 2009, p 6Google Scholar
  6. Lorenzo-Ginori J, Cruz-Enriquez H (2005) De-noising method in the wavelet packets domain for phase images. In: CIARP 2005, Springer-Verlag, pp 593–600Google Scholar
  7. MacKay D (2003) Information theory, inference and learning algorithms. Cambridge University Press, New York City, New York 10013-2473, USAGoogle Scholar
  8. Mahmoud R, Faheem M, Sarhan A (2008) Intelligent denoising technique for spatial video denoising for real-time applications. In: Proceedings of 2008 international conference on computer engineering & systems, Ain Shams University, Cairo, pp 407–12Google Scholar
  9. Ye Z (2005) Artificial intelligence approach for biomedical sample characterization using Raman spectroscopy. IEEE Trans Autom Sci Eng 2(1):67–73CrossRefGoogle Scholar
  10. Ye Z, Ye Y, Mohamadian H, Bhattacharya P (2005) Fuzzy filtering and fuzzy K-means clustering on biomedical sample characterization. In: Proceedings of 2005 IEEE international conference on control applications, Toronto, Aug 2005, pp 90–95Google Scholar
  11. Ye Z, Luo J, Bhattacharya P, Ye Y (2006) Segmentation of aerial images and satellite images using unsupervised nonlinear approach. WSEAS Trans Syst 5(2):333–339Google Scholar
  12. Ye Z, Mohamadian H, Ye Y (2007) Information measures for biometric identification via 2D discrete wavelet transform. In: Proceedings of the 2007 IEEE international conference on automation science and engineering, Scottsdale, 22–25 Sept 2007, pp 835–840Google Scholar
  13. Ye Z, Mohamadian H, Ye Y (2007) Discrete entropy and relative entropy study on nonlinear clustering of underwater and arial images. In: Proceedings of the 2007 IEEE international conference on control applications, Oct 2007, pp 318–323Google Scholar
  14. Ye Z, Cao H, Iyengar S, Mohamadian H (2008) Medical and biometric system identification for pattern recognition and data fusion with quantitative measuring. Systems engineering approach to medical automation, Chapter Six, Artech House Publishers, pp 91–112, ISBN978-1-59693-164-0Google Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Department of Electrical EngineeringSouthern UniversityBaton RougeUSA
  2. 2.College of EngineeringSouthern UniversityBaton RougeUSA

Personalised recommendations