Application of Fuzzy C-Means Algorithm in Complex Background Image Segmentation of Forensic Science

  • Zhuang Chen
  • ChunYu LiEmail author
  • ZhanQing Jiang
  • Yongqiang Zhao
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 517)


In the field of forensic science, image segmentation is required as a basic and significant stage in forensic image analysis. It is very important to segment the stamp impression image with a complex background precisely. This paper puts forward a feasible and efficient approach for complex background stamp impression image segmentation based on Fuzzy C-Means (FCM) algorithm. The fuzzy feature of forensic image can be handled efficiently using Fuzzy C-Means (FCM) algorithm in the forensic science field. The results of the experiments demonstrate the validity and accuracy of Fuzzy C-Means (FCM) algorithm.


Image segmentation Fuzzy C-Means Forensic science Stamp impression Complex background 



This work was supported by the National Key Research and Development Plan (2017YFC0822004) and by the Key Project of Basic Scientific Research Service Fee of People’s Public Security University of China (2018JKF220). The authors would like to thank the editorial team and reviewers for supporting this paper.

Heartfelt thanks are also given for the comments and contributions of reviewers and members of the editorial team.


  1. 1.
    Pal, N.R.: A review on image segmentation techniques. Pattern Recognit. 26(9), 1277–1294 (1993)CrossRefGoogle Scholar
  2. 2.
    Shantaiya, S., Verma, K., Mehta, K.K.: Multiple object clustering using fcm and k-means algorithms. Int. J. Comput. Vis. Robot. 6(4), 331 (2016)CrossRefGoogle Scholar
  3. 3.
    APAKang, J.Y., Gong, C.L., Zhang, W.J.: Fingerprint image segmentation using modified fuzzy c-means algorithm (report). J. Biomed. Sci. Eng. 2(8), 656–660 (2009)Google Scholar
  4. 4.
    Shi, S.P., Yang, X.U., Qian, H.G., Che, X.U.: Issues related to examination of stamp impressions: identification of stamp impressions forged by high simulation techniques. Chin. J. Forensic Sci. (2008)Google Scholar
  5. 5.
    Zhen, D., Zhongshan, H., Jingyu, Y., Zhenmin, T., Yongge, W.: A quick fcm algorithm for gray images segmentation. Pattern Recognit. Artif. Intel. (1997)Google Scholar
  6. 6.
    Pal, N.R., Bezdek, J.C.: On cluster validity for the fuzzy c-means model. IEEE Trans. Fuzzy Syst. 3(3), 370–379 (2002)CrossRefGoogle Scholar
  7. 7.
    Yu, J., Yang, M.: A study on a generalized fcm. Lect. Notes Comput. Sci. 2639, 390–393 (2003)CrossRefGoogle Scholar
  8. 8.
    Boss, R.S.C., Thangavel, K., Daniel, D.A.P.: Mammogram image segmentation using fuzzy clustering. In: International Conference on Pattern Recognition, Informatics and Medical Engineering, vol. 02, pp. 290–295. IEEE (2012)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Zhuang Chen
    • 1
  • ChunYu Li
    • 1
    Email author
  • ZhanQing Jiang
    • 1
  • Yongqiang Zhao
    • 1
  1. 1.Forensic image technology direction, People’s Public Security, University of China (PPSUC)BeijingPeople’s Republic of China

Personalised recommendations