Validating Few Contemporary Approaches in Image Segmentation – A Quantitative Approach

  • Syed FasiuddinEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 968)


In this paper, we present an extensive study and quantitative evaluation of six segmentation techniques on images of Berkeley Segmentation Database. Image segmentation plays a vital role in many computer vision applications and benchmarking such algorithms may assist research community in present and future research efforts in the field of image segmentation. Color space models, Hybrid color space and wavelet, Gradient Magnitude Techniques, K – means, C-Means & Fuzzy C-Means (FCM) and Edison’s Mean – shift approaches are evaluated using at least six metrics with respect to ground-truth boundaries of entire images in BSD 300/500 dataset images. The results stated here gives useful insights to above mentioned approaches and its significance in aligning upcoming research avenues in image segmentation.


Computer vision Image segmentation Quantitative analysis Contemporary approaches 


  1. 1.
    Fram, J.R., Deutsch, E.S.: On the quantitative evaluation of edge detection schemes and their comparison with human performances. IEEE Trans. Comput. C-24, 616–628 (1975)Google Scholar
  2. 2.
    Woods, R.E., Gonzalez, R.C.: Digital Image Processing. Prentice Hall, Upper Saddle River (2002)Google Scholar
  3. 3.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 889–905 (2000)Google Scholar
  4. 4.
    Huttenlocher, D., Felzenszwalb, P.: Image segmentation using local variation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 98–104 (1998)Google Scholar
  5. 5.
    Yimin, Z., Wenbing, T., Hai, J.: Color image segmentation based on mean shift and normalized cuts. IEEE Trans. Syst. Man Cybern. Part B Cybern. 37, 1382–1389 (2007)Google Scholar
  6. 6.
    Siskind, J.M., Wang, S.: Image segmentation with ratio cut. IEEE Trans. Pattern Anal. Mach. Intell. 25, 675–690 (2003)CrossRefGoogle Scholar
  7. 7.
    Siarry, P., Hammouche, K., Diaf, M.: A multilevel automatic thresholding method based on a genetic algorithm for a fast image segmentation. Comput. Vis. Image Underst. 109, 163–175 (2008)Google Scholar
  8. 8.
    Diaf, M., Siarry, P., Dirami, A., Hammouche, K.: Fast multilevel thresholding for image segmentation through a multiphase level set method. Sig. Process. 93, 139–153 (2013)Google Scholar
  9. 9.
    Wanga, Q.-Y., Yang, H.-Y., Wang, X.-Y., Zhang, X.-J.: LSSVM based image segmentation using color and texture information. J. Vis. Commun. Image R. 23, 1095–1112 (2012)Google Scholar
  10. 10.
    Malik, J., Arbelaez, P., Bourdev, L.: Semantic segmentation using regions and parts. In: CVPR, pp. 3378–3385. IEEE (2012)Google Scholar
  11. 11.
    Mahantesh, K., Aradhya, V.N.M., Naveena, C.: An impact of complex hybrid color space in image segmentation. In: The Proceedings of 2nd International Symposium on Intelligent Informatics (ISI13), Mysore, India, vol. 235, pp. 73–82 (2013)Google Scholar
  12. 12.
    Malik, J., Maji, S.: Object detection using a max-margin hough transform. In: CVPR, pp. 1038–1045. IEEE (2009)Google Scholar
  13. 13.
    Meer, P., Comaniciu, D.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 603–619 (2002)Google Scholar
  14. 14.
    Jepson, A.D., Estrada, F.J.: Benchmarking image segmentation algorithms. Int. J. Comput. Vis. 85, 167–181 (2009)Google Scholar
  15. 15.
    Blake, A., Rother, A., Brown, M., Perez, P., Torr, P.: Interactive image segmentation using an adaptive GMMRF model. In: European Conference on Computer Vision, pp. 428–441 (2004)Google Scholar
  16. 16.
    Meer, P., Comaniciu, D.: Robust analysis of feature spaces: color image segmentation. In: IEEE Computer Vision and Pattern Recognition, pp. 750–755 (1997)Google Scholar
  17. 17.
    Fowlkes, C., Martin, D., Malik, J.: Learning to detect natural image boundaries using local brightness, color and texture cues. IEEE-PAMI 26, 530–549 (2004)CrossRefGoogle Scholar
  18. 18.
    Mahantesh, K., Aradhya, V.N.M., Niranjan, S.K.: Coslets: a novel approach to explore object taxonomy in compressed DCT domain for large image datasets. In: El-Alfy, El.M., Thampi, S.M., Takagi, H., Piramuthu, S., Hanne, T. (eds.) Advances in Intelligent Informatics. AISC, vol. 320, pp. 39–48. Springer, Cham (2015). Scholar
  19. 19.
    Mahantesh, K., Aradhya, V.N.M., Sandesh Kumar, B.V.: Benchmarking gradient magnitude techniques for image segmentation using CBIR. In: Prasath, R., Vuppala, A.K., Kathirvalavakumar, T. (eds.) MIKE 2015. LNCS (LNAI), vol. 9468, pp. 259–268. Springer, Cham (2015). Scholar
  20. 20.
    Manjunath, B.S.: Image browsing in the Alexandria digital library project. D-Lib Magazine (1995).
  21. 21.
    Yanga, H.-Y., Bu, J., Wanga, X.-Y., Zhanga, X.-J.: A pixel-based color image segmentation using support vector machine and fuzzy c-means. Neural Netw. 33, 148–159 (2012)Google Scholar
  22. 22.
    Fowlkes, C., Maire, M., Arbelaez, P., Malik, J.: Using contours to detect and localize junctions in natural images. In: CVPR, pp. 1–8. IEEE (2008)Google Scholar
  23. 23.
    Fowlkes, C., Malik, J., Arbelaez, P., Maire, M.: Contour detection and hierarchical image segmentation. IEEE PAMI 33, 898–916 (2011)CrossRefGoogle Scholar
  24. 24.
    Yu, S.X.: Segmentation induced by scale invariance. In: IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 444–451 (2005)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Blackbuck Engineers Pvt LtdHyderabadIndia

Personalised recommendations