Edge Preserving Region Growing for Aerial Color Image Segmentation

  • Badri Narayan Subudhi
  • Ishan Patwa
  • Ashish Ghosh
  • Sung-Bae Cho
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 309)


Many image segmentation techniques are available in the literature. One of the most popular techniques is region growing. Research on region growing, however, has focused primarily on the design of feature extraction and on growing and merging criterion. Most of these methods have an inherent dependence on the order in which the points and regions are examined. This weakness implies that a desired segmented result is sensitive to the selection of the initial growing points and prone to over-segmentation. This paper presents a novel framework for avoiding anomalies like over-segmentation. In this article, we have proposed an edge preserving segmentation technique for segmenting aerial images. The approach implicates the preservation of edges prior to segmentation of images, thereby detecting even the feeble discontinuities. The proposed scheme is tested on two challenging aerial images. Its effectiveness is provided by comparing its results with those of the state-of-the-art techniques and the results are found to be better.


Image segmentation Region growing Edge detection Thresholding Aerial image 


  1. 1.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Pearson Education, Singapore (2001)Google Scholar
  2. 2.
    Pun, T.: Entropic thresholding. A new approach. Comput. Graph. Image Process. 16, 210–236 (1981)CrossRefGoogle Scholar
  3. 3.
    Peak, J., Tag, P.: Segmentation of satellite weather imagery using hierarchical thresholding and neural networks. J. Appl. Meteorol. 33, 605–616 (1994)CrossRefGoogle Scholar
  4. 4.
    Ghosh, A., Subudhi, B.N., Ghosh, S.: Object detection from videos captured by moving camera by fuzzy edge incorporated markov random field and local histogram matching. IEEE Trans. Circuits Syst. Video Technol. 22(8), 1127–1135 (2012)CrossRefGoogle Scholar
  5. 5.
    Berthod, M., Kato, Z., Yu, S., Zerubia, J.: Bayesian image classification using markov random fields. Image Vis. Comput. 14, 285–295 (1996)CrossRefGoogle Scholar
  6. 6.
    Zucker, S.W.: Region growing: childhood and adolescence. Comput. Graph. Image Process. 5, 382–399 (1976)CrossRefGoogle Scholar
  7. 7.
    Kim, B.-G., Shim, J.-I., Park, T.-J.: Unsupervised video object segmentation and tracking based on new edge features. Pattern Recogn. Lett. 25, 1731–1742 (2004)CrossRefGoogle Scholar
  8. 8.
    Hu, X., Tao, C.V., Prenzel, B.: Automatic segmentation of high-resolution satellite imagery by integrating texture, intensity, and color features. Photogram. Eng. Remote Sens. 71(12), 1399–1406 (2005)CrossRefGoogle Scholar
  9. 9.
    Hojjatoleslami, S.A., Kittler, J.: Region growing: a new approach. IEEE Trans. Image Process. 7, 1079–1084 (1998)CrossRefGoogle Scholar
  10. 10.
    Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 603–619 (2002)CrossRefGoogle Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  • Badri Narayan Subudhi
    • 1
  • Ishan Patwa
    • 2
  • Ashish Ghosh
    • 1
  • Sung-Bae Cho
    • 3
  1. 1.Machine Intelligence UnitIndian Statistical InstituteKolkataIndia
  2. 2.Department of Instrumentation and Control EngineeringNational Institute of TechnologyTiruchirappalliIndia
  3. 3.Soft Computing Laboratory, Department of Computer ScienceYonsei UniversitySeoulSouth Korea

Personalised recommendations