Advertisement

Object Detection in Images Based on Homogeneous Region Segmentation

  • Abdesalam Amrane
  • Abdelkrim Meziane
  • Nour El Houda Boulkrinat
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10868)

Abstract

Image segmentation for object detection is one of the most fundamental problems in computer vision, especially in object-region extraction task. Most popular approaches in the segmentation/object detection tasks use sliding-window or super-pixel labeling methods. The first method suffers from the number of window proposals, whereas the second suffers from the over-segmentation problem. To overcome these limitations, we present two strategies: the first one is a fast algorithm based on the region growing method for segmenting images into homogeneous regions. In the second one, we present a new technique for similar region merging, based on a three similarity measures, and computed using the region adjacency matrix. All of these methods are evaluated and compared to other state-of-the-art approaches that were applied on the Berkeley image database. The experimentations yielded promising results and would be used for future directions in our work.

Keywords

Region proposal Region growing Region merging Image segmentation 

References

  1. 1.
    Krahenbuhl, A.: Segmentation et analyse géométrique: application aux images tomodensitométriques de bois. Thesis, Université de Lorraine (2014)Google Scholar
  2. 2.
    Peng, B., Zhang, L., Zhang, D.: Automatic image segmentation by dynamic region merging. IEEE Trans. Image Process. 20(12), 3592–3605 (2011)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Hedberg, H.: A survey of various image segmentation techniques. Department of Electroscience, Box 118 (2010)Google Scholar
  4. 4.
    Fox, V., Milanova, M., Al-Ali, S.: A hybrid morphological active contour for natural images. Int. J. Comput. Sci. Eng. Appl. 3(4), 1–13 (2013)Google Scholar
  5. 5.
    Niyas, S., Reshma, P., Thampi, S.M.: A color image segmentation scheme for extracting foreground from images with unconstrained lighting conditions. Intelligent Systems Technologies and Applications 2016. AISC, vol. 530, pp. 3–19. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-47952-1_1CrossRefGoogle Scholar
  6. 6.
    Heisele, B.: Visual object recognition with supervised learning. IEEE Intell. Syst. 18(3), 38–42 (2003)CrossRefGoogle Scholar
  7. 7.
    Erhan, D., Szegedy, C., Toshev A., Anguelov D.: Scalable object detection using deep neural networks. In: CVPR (2014)Google Scholar
  8. 8.
    Bappy, J.H., Roy-Chowdhury, A.: CNN based region proposals for efficient object detection. In: IEEE International Conference on Image Processing (ICIP) (2016)Google Scholar
  9. 9.
    Yan, J., Yu, Y., Zhu, X., Lei, Z., Li, S.Z.: Object detection by labeling superpixels. In: CVPR (2015)Google Scholar
  10. 10.
    Blasiak, A.: A Comparison of image segmentation methods. Thesis in Computer Science (2007)Google Scholar
  11. 11.
    Pantofaru, C., Hebert, M.: A comparison of image segmentation algorithms. Carnegie Mellon University (2005)Google Scholar
  12. 12.
    Robinson, D.J., Redding, N.J., Crisp, D.J.: Implementation of a fast algorithm for segmenting SAR imagery. Scientific and Technical report, Defense Science and Technology Organization, Australia (2002)Google Scholar
  13. 13.
    Rosenberger, C., Chabrier, S., Laurent, H., Emile, B.: Unsupervised and supervised image segmentation evaluation. Adv. Image Video Segm. 29(1), 365–393 (2006)CrossRefGoogle Scholar
  14. 14.
    Zhang, Y.J.: A survey on evaluation methods for image segmentation. Pattern Recognit. 29, 1335–1346 (1996)CrossRefGoogle Scholar
  15. 15.
    Li, S., Wu, D.O.: Modularity-based image segmentation. IEEE Trans. Circ. Syst. Video Technol. 25(4), 570–581 (2015)CrossRefGoogle Scholar
  16. 16.
    Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)CrossRefGoogle Scholar
  17. 17.
    Rao, S.R., Mobahi, H., Yang, A.Y., Sastry, S.S., Ma, Y.: Natural image segmentation with adaptive texture and boundary encoding. In: Zha, H., Taniguchi, R., Maybank, S. (eds.) ACCV 2009. LNCS, vol. 5994, pp. 135–146. Springer, Heidelberg (2010).  https://doi.org/10.1007/978-3-642-12307-8_13CrossRefGoogle Scholar
  18. 18.
    Browet, A., Absil, P.-A., Van Dooren, P.: Community detection for hierarchical image segmentation. In: Aggarwal, J.K., Barneva, R.P., Brimkov, V.E., Koroutchev, K.N., Korutcheva, E.R. (eds.) IWCIA 2011. LNCS, vol. 6636, pp. 358–371. Springer, Heidelberg (2011).  https://doi.org/10.1007/978-3-642-21073-0_32CrossRefMATHGoogle Scholar
  19. 19.
    Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 32(7), 1271–1283 (2010)CrossRefGoogle Scholar
  20. 20.
    Soille, P.: Morphological Image Analysis: Principles and Applications. Springer, Berlin (2004).  https://doi.org/10.1007/978-3-662-05088-0CrossRefMATHGoogle Scholar
  21. 21.
    Cour, T., Benezit, F., Shi, J.: Spectral segmentation with multiscale graph decomposition. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR, vol. 2, pp. 1124–1131. IEEE (2005)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Abdesalam Amrane
    • 1
    • 2
  • Abdelkrim Meziane
    • 1
  • Nour El Houda Boulkrinat
    • 1
  1. 1.Research Center on Scientific and Technical Information (CERIST)Ben AknounAlgeria
  2. 2.Université Abderrahmane Mira BéjaiaBéjaiaAlgeria

Personalised recommendations