Pattern Analysis and Applications

, Volume 22, Issue 1, pp 75–88 | Cite as

An image thresholding approach based on Gaussian mixture model

  • Like Zhao
  • Shunyi ZhengEmail author
  • Wenjing Yang
  • Haitao Wei
  • Xia Huang
Theoretical advances


Image thresholding is an important technique for partitioning the image into foreground and background in image processing and analysis. It is difficult for traditional thresholding methods to get satisfactory performance on the noisy and uneven grayscale images. In this paper, we propose an image thresholding approach based on Gaussian mixture model (GMM) to solve this problem. GMM assumes that image is a mixture of two unknown parameters’ Gaussian distributions, which corresponds to foreground and background, respectively. Based on this assumption, we adopt expectation maximization algorithm with a simple initialization strategy to estimate the statistical parameters and utilize Bayesian criteria to generate the binary map. Furthermore, we calculate the posterior probabilities in consideration of neighborhood effect to achieve good performance on noisy and uneven grayscale images. Experimental results conducted on the synthetic and real images demonstrate the effectiveness of the proposed method.


Image thresholding Gaussian mixture model EM algorithm Neighborhood information 



This work was supported by the National Natural Science Foundation of China (Grant Nos. 41671452, 41701532), High-level talent Fund Project of Henan University of Technology (Grant No. 2018BS054) and the basic research funding of the Central University (Grant No. 2042016kf0012).


  1. 1.
    Nie F, Zhang P, Li J et al (2017) A novel generalized entropy and its application in image thresholding. Signal Process 134:23–34Google Scholar
  2. 2.
    Sujaritha M, Annadurai S (2011) A new modified Gaussian mixture model for color-texture segmentation. J Comput Sci 7(2):279–283Google Scholar
  3. 3.
    Guo Y, Şengür A, Ye J (2014) A novel image thresholding algorithm based on neutrosophic similarity score. Measurement 58:175–186Google Scholar
  4. 4.
    Ueno K, Yamaguchi J (2012) Image thresholding by improved convergent floating thresholding method using extended control value. IEEJ Trans Electron Inf Syst 132:759–765Google Scholar
  5. 5.
    Li Z, Liu C, Liu G et al (2010) A novel statistical image thresholding method. AEU Int J Electron Commun 64(2):1137–1147Google Scholar
  6. 6.
    Zou Y, Dong F, Lei B et al (2014) Maximum similarity thresholding. Digit Signal Process 28(1):120–135Google Scholar
  7. 7.
    Sezgin M, Sankur B (2004) Survey over image thresholding techniques and quantitative performance evaluation. J Electron Imaging 13(1):146–166Google Scholar
  8. 8.
    Chakrawarty P, Bhatnagar G (2016) Image thresholding based on local activity feature matrix. Opt Int J Light Electron Opt 127(20):9037–9045Google Scholar
  9. 9.
    Ahmadi E, Azimifar Z, Shams M et al (2015) Document image binarization using a discriminative structural classifier. Pattern Recogn Lett 63:36–42Google Scholar
  10. 10.
    Makridis M, Papamarkos N (2010) An adaptive layer-based local binarization technique for degraded documents. Int J Pattern Recog Artif Intell 24(2):245–279Google Scholar
  11. 11.
    Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):377–393Google Scholar
  12. 12.
    Kittler J, Illingworth J (1986) Minimum error thresholding. Pattern Recogn 19(1):41–47Google Scholar
  13. 13.
    Sauvola J, Pietikäinen M (2000) Adaptive document image binarization. Pattern Recogn 33(2):225–236Google Scholar
  14. 14.
    Moghaddam RF, Cheriet M (2010) A multi-scale framework for adaptive binarization of degraded document images. Pattern Recogn 43(6):2186–2198zbMATHGoogle Scholar
  15. 15.
    Bernsen J (1986) Dynamic thresholding of gray-level images. In: International conference on pattern recognition, pp 251–255Google Scholar
  16. 16.
    Gatos B, Pratikakis I, Perantonis SJ (2006) Adaptive degraded document image binarization. Pattern Recogn 39(3):317–327zbMATHGoogle Scholar
  17. 17.
    Ben Ishak A (2016) A two-dimensional multilevel thresholding method for image segmentation. Appl Soft Comput 52:306–322Google Scholar
  18. 18.
    Bazi Y, Bruzzone L, Melgani F (2007) Image thresholding based on the EM algorithm and the generalized Gaussian distribution. Pattern Recognit 40(2):619–634zbMATHGoogle Scholar
  19. 19.
    Huang ZK, Chau KW (2008) A new image thresholding method based on Gaussian mixture model. Appl Math Comput 205(2):899–907MathSciNetzbMATHGoogle Scholar
  20. 20.
    Kurita T, Otsu N, Abdelmalek N (1992) Maximum likelihood thresholding based on population mixture models. Pattern Recogn 25(10):1231–1240Google Scholar
  21. 21.
    Jiang Y, Yang Z, Hao Z, Wang Y (2014) A cooperative honey bee mating algorithm and its application in multi-threshold image segmentation. In: IEEE congress on evolutionary computation, pp 1579–1585Google Scholar
  22. 22.
    Kotte S, Kumar PR, Injeti SK (2018) An efficient approach for optimal multilevel thresholding selection for gray scale images based on improved differential search algorithm. Ain Shams Eng J 9(4):1043–1067Google Scholar
  23. 23.
    Cuevas E, Zaldivar D, Pérez-Cisneros M (2011) Seeking multi-thresholds for image segmentation with Learning Automata. Mach Vis Appl 22(5):805–818Google Scholar
  24. 24.
    Singh A, Baraskar T (2016) A survey on multi-level thresholding for image segmentation using nature inspired algorithms. In: International conference on electrical, electronics, engineering trends, communication, optimization and sciences, pp 878–883Google Scholar
  25. 25.
    Tobias OJ, Seara R (2002) Image segmentation by histogram thresholding using fuzzy sets. IEEE Trans Image Process 11(12):1457–1465Google Scholar
  26. 26.
    Han J, Yang C, Zhou X, Gui W (2017) A new multi-threshold image segmentation approach using state transition algorithm. Appl Math Model 44:588–601MathSciNetGoogle Scholar
  27. 27.
    Gupta L, Sortrakul T (1998) A Gaussian-mixture-based image segmentation algorithm. Pattern Recogn 31(3):315–325Google Scholar
  28. 28.
    Hui T, Dillenseger JL, Xu DB, Li ML (2009) A vectorial image soft segmentation method based on neighborhood weighted Gaussian mixture model. Comput Med Imaging Graph 33(8):644–650Google Scholar
  29. 29.
    Zhu F, Luo L, Song Y et al (2011) Adaptive spatially neighborhood information Gaussian mixture model for image segmentation. J Comput Res Dev 48(11):2000–2007Google Scholar
  30. 30.
    Li SZ, Jain AK (2015) Encyclopedia of biometrics, 2nd edn. Springer, New YorkGoogle Scholar
  31. 31.
    Xiong TS, Huang YY (2015) Robust Gaussian mixture modelling based on spatially constraints for image segmentation. J Inf Hiding Multimed Signal Process 6(5):857–868Google Scholar
  32. 32.
    Dempster AP (1977) Maximum likelihood estimation from incomplete data via the EM algorithm. J R Stat Soc 39(1):1–38zbMATHGoogle Scholar
  33. 33.
    Mclachlan GJ, Peel D (2004) Finite mixture models. Springer, New YorkzbMATHGoogle Scholar
  34. 34.
    Sha C, Hou J, Cui H (2016) A robust 2D Otsu’s thresholding method in image segmentation. J Vis Commun Image Represent 41:339–351Google Scholar
  35. 35.
    Sezgin M, Sankur B (2001) Selection of thresholding methods for nondestructive testing applications. In: International conference on image processing, vol 3, pp 764–767Google Scholar
  36. 36.
    Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26(3):297–302Google Scholar
  37. 37.
    Niblack W (1986) An introduction to digital image processing. Prentice Hall, Englewood CliffsGoogle Scholar
  38. 38.
    Gong J, Li L, Chen W (1996) A fast recursive algorithm for two-dimensional thresholding. In: International conference on signal processing, vol 2, pp 1155–1158Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  • Like Zhao
    • 1
    • 2
  • Shunyi Zheng
    • 2
    • 3
    Email author
  • Wenjing Yang
    • 2
  • Haitao Wei
    • 2
    • 4
  • Xia Huang
    • 2
    • 3
  1. 1.College of Information Science and EngineeringHenan University of TechnologyZhengzhouChina
  2. 2.School of Remote Sensing and Information EngineeringWuhan UniversityWuhan CityChina
  3. 3.Collaborative Innovation Center of Geospatial TechnologyWuhan CityChina
  4. 4.Institute of Smart CityZhengzhou UniversityZhengzhouChina

Personalised recommendations