Advertisement

Comparison of Moving Object Segmentation Techniques

  • Yaecob Girmay Gezahegn
  • Abrham Kahsay Gebreselasie
  • Dereje H. Mariam W. Gebreal
  • Maarig Aregawi Hagos
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 244)

Abstract

Moving object segmentation is the extraction of meaningful features from series of images. In this paper, different types of moving object segmentation techniques such as Principal Component Analysis (PCA), K-Means clustering (KM), Genetic Algorithm (GA) and Genetic Algorithm Initialized K-means clustering (GAIK) have been compared. From our analysis we have observed that PCA reduces dimension or size of data for further processing, which in return reduces the computational time. However, the segmentation quality sometimes becomes unacceptable. On the other hand, due to random initialization of its centroids, KM clustering sometimes converges to local minimum which results in bad segmentation. Another algorithm which has been considered in this study is GA, which searches all the feature space and results in a global optimum clustering. Although the segmentation quality is good, it is computationally expensive. To mitigate these problems, KM and GA are merged to form GAIK, where GA helps to initialize the centroids of the clustering. From our study, it has been found out that GAIK is superior to GA in both the quality of segmentation and computational time. Therefore, in general, the analyses of the four algorithms shows that GAIK is optimal for segmenting a moving object.

Keywords

Clustering Segmentation PCA KM GA GAIK 

References

  1. 1.
    Otsu, N: Discriminant and least square threshold selection. In: Proceedings of the 4th International Joint Conference on Pattern Recognition, pp. 592–596 (1978)Google Scholar
  2. 2.
    Wang, et al.: Threshold segmentation for hand vein image. In: Control Theory and Application, pp. 19–22. Publishing House of Electronics Industry, Beijing (2005)Google Scholar
  3. 3.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Mach. Intell. 22, 888–905 (2000)CrossRefGoogle Scholar
  4. 4.
    Han, J., Kamber, M.: Data Mining: Concepts and Techniques. Morgan Kaufmann Publishers, Burlington (2001)zbMATHGoogle Scholar
  5. 5.
    Pena, J., Lozano, J., Larranaga, P.: An empirical comparison of four initialization methods for the K-means algorithm. Pattern Recogn. Lett. 20(10), 1027–1040 (1999)CrossRefGoogle Scholar
  6. 6.
    Kaufman, L., Rousseeuw, P.: Finding Groups in Data: An Introduction To Cluster Analysis. Wiley, Hoboken (1990)CrossRefGoogle Scholar
  7. 7.
    Jeyakumari, D., Somasundareswari, D.: Analysis on genetic current trends in color image segmentation. Int. J. Mod. Sci. Eng. Technol. (IJMSET) 1(5), 1–12 (2014)Google Scholar
  8. 8.
    Gao, X.: Fuzzy Cluster Analysis and Application, pp. 124–130. Xidian University Press, Xi’an (2004)Google Scholar
  9. 9.
    Wang, Q.: One image segmentation technique based on wavelet analysis in the context of texture. In: Data Collection and Processing, vol. 13, p. 1216 (1998)Google Scholar
  10. 10.
    Kang, W.X., et al.: The comparative research on image segmentation algorithms. In: IEEE, First International Workshop on Education Technology and Computer Science, pp. 703–707 (2009)Google Scholar
  11. 11.
  12. 12.
    Dubes, R.C., Jain, A.K.: Clustering techniques: the user’s dilemma. Pattern Recogn. 8(4), 247–260 (1976)CrossRefGoogle Scholar
  13. 13.
    Maulik, U., Bandyopadhyay, S.: Genetic algorithm based clustering technique. Pattern Recogn. 33(9), 1455–1465 (2000)CrossRefGoogle Scholar
  14. 14.
    Fogel, D.B.: An introduction to simulated evolutionary optimization. IEEE Trans. Neural Netw. 5(1), 3–14 (1994)CrossRefGoogle Scholar
  15. 15.
  16. 16.
    Lu, Y., Lu, S., Fotouhi, F., Deng, Y., Brown, S.: FGKA: a fast genetic k-means clustering algorithm. In: ACM Symposium on Applied Computing (2004)Google Scholar
  17. 17.
    Krishna, K., Murty, M.N.: Genetic k-means algorithm. IEEE Trans. Syst. Man Cybern. Part B Cybern. 29(3), 433–439 (1999)CrossRefGoogle Scholar
  18. 18.

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018

Authors and Affiliations

  • Yaecob Girmay Gezahegn
    • 1
  • Abrham Kahsay Gebreselasie
    • 2
  • Dereje H. Mariam W. Gebreal
    • 1
  • Maarig Aregawi Hagos
    • 3
  1. 1.Addis Ababa UniversityAddis AbabaEthiopia
  2. 2.Addis Ababa Science and Technology UniversityAddis AbabaEthiopia
  3. 3.Mekelle UniversityMekelleEthiopia

Personalised recommendations