Automated Histogram-Based Seed Selection for the Segmentation of Natural Scene

  • R. AarthiEmail author
  • S. Shanmuga Priya
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 766)


Images have been widely used in today’s life varying from personal usage with Flickr, Facebook to the analysis of hyperspectral images. Availability of such huge volume of images in digital form requires an automatic analysis on visual content. The major challenge in content labeling is in segmentation, which divides the image into regions. Our work focuses on the segmentation technique that adapts based on regions in the natural images. The proposed method used automatic seed selection by analyzing the dynamic color distribution of the image. The experimental results on datasets show the better performance of our method.


Histogram Seeded region Segmentation 


  1. 1.
    Raghesh Krishnan, K., Radhakrishnan, S.: Focal and diffused liver disease classification from ultrasound images based on isocontour segmentation. IET Image Process. 9, (4, 1), 261–270 (2015)Google Scholar
  2. 2.
    Vogel, J., Schwaninger, A.: Categorization of natural scenes: local vs global information, University of British Columbia (2001)Google Scholar
  3. 3.
    Kumar, D.A., Kannathasan, N.: A study and characterization of chemical properties of soil surface data using K-means algorithm. In: Proceedings of the 2013 International Conference on Pattern Recognition, Informatics and Mobile Engineering (PRIME) 21–22 February, (2013). 978-1-4673-5845-3/13Google Scholar
  4. 4.
    Sert, E., Okumus, I.T.: Segmentation of mushroom and cap width measurement using modified K-means clustering algorithm. In: Digital Image Processing and Computer Graphics, Vol. 12, Issue 4 (2014)Google Scholar
  5. 5.
    Siddiqui, F.U., Isa, N.AM., Member, IEEE.: Enhanced moving K-Means (EMKM) algorithm for image segmentation. IEEE Trans. Consum. Electron. 57(2) (2011)CrossRefGoogle Scholar
  6. 6.
    Raju, P.D.R. et al.: Image segmentation by using histogram thresholding. IJCSET, 2(1), 776–779 (2012)Google Scholar
  7. 7.
    Elmoufidi, A., Student Member IEEE, et al.: Automatically density based breast segmentation for mammograms by using dynamic k-means algorithm and seed based region growing. In: IEEE Instrumentation and Measurement Society, pp. 533–538., 2015
  8. 8.
    Genovez, P. et al.: An image-segmentation-based framework to detect oil slicks from moving vessels in the Southern African oceans using SAR imagery. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. 99, 1–9 (2017)Google Scholar
  9. 9.
    Machine learning data website available
  10. 10.
    Kachouri, R., Soua, M., Akil, M.: Unsupervised image segmentation based on local pixel clustering and Low-Level region merging. In: 2nd IEEE International Conference on Advanced Technologies for Signal and Image Processing ATSIP’. Monastir, Tunisia, vol. 16, (2016)Google Scholar
  11. 11.
    Aarthi, R., Padmavathi, S., Amudha J.: Vehicle detection in static images using color and corner map. In: International Conference on Recent Trends in Information, Telecommunication and Computing, kochi. pp. 12–13 (2010)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringAmrita School of EngineeringCoimbatoreIndia
  2. 2.Amrita Vishwa VidyapeethamCoimbatoreIndia

Personalised recommendations