Interactive Image Segmentation Using an Adaptive GMMRF Model

  • Andrew Blake
  • Carsten Rother
  • M. Brown
  • Patrick Perez
  • Philip Torr
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3021)


The problem of interactive foreground/background segmentation in still images is of great practical importance in image editing. The state of the art in interactive segmentation is probably represented by the graph cut algorithm of Boykov and Jolly (ICCV 2001). Its underlying model uses both colour and contrast information, together with a strong prior for region coherence. Estimation is performed by solving a graph cut problem for which very efficient algorithms have recently been developed. However the model depends on parameters which must be set by hand and the aim of this work is for those constants to be learned from image data.

First, a generative, probabilistic formulation of the model is set out in terms of a “Gaussian Mixture Markov Random Field” (GMMRF). Secondly, a pseudolikelihood algorithm is derived which jointly learns the colour mixture and coherence parameters for foreground and background respectively. Error rates for GMMRF segmentation are calculated throughout using a new image database, available on the web, with ground truth provided by a human segmenter. The graph cut algorithm, using the learned parameters, generates good object-segmentations with little interaction. However, pseudolikelihood learning proves to be frail, which limits the complexity of usable models, and hence also the achievable error rate.


Partition Function Ising Model Spatial Interaction Foreground Object Parameter Learning 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Chuang, Y.Y., Curless, B., Salesin, D., Szeliski, R.: A Bayesian approach to digital matting. In: Proc. Conf. Computer Vision and Pattern Recognition, CD–ROM (2001)Google Scholar
  2. 2.
    Ruzon, M., Tomasi, C.: Alpha estimation in natural images. In: Proc. Conf. ComputerVision and Pattern Recognition, pp. 18–25 (2000)Google Scholar
  3. 3.
    Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In: Proc. Int. Conf. on Computer Vision, CD–ROM (2001)Google Scholar
  4. 4.
    Greig, D., Porteous, B., Seheult, A.: Exact MAP estimation for binary images. J. Royal Statistical Society 51, 271–279 (1989)Google Scholar
  5. 5.
    Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? IEEE Trans. on Pattern Analysis and Machine Intelligence (2003) (in press)Google Scholar
  6. 6.
    Besag, J.: On the statistical analysis of dirty pictures. J. Roy. Stat. Soc. Lond. B. 48, 259–302 (1986)zbMATHMathSciNetGoogle Scholar
  7. 7.
    Winkler, G.: Image analysis, random fields and dynamic Monte Carlo methods. Springer, Heidelberg (1995)zbMATHGoogle Scholar
  8. 8.
    Kumar, S., Hebert, M.: Discriminative random fields:A discriminative framework for contextual interaction in classification. In: Proc. Int. Conf. on Computer Vision, CD–ROM (2003)Google Scholar
  9. 9.
    Descombes, X., Sigelle, M., Preteux, F.: GMRF parameter estimation in a non-stationary framework by a renormalization technique. IEEE Trans. Image Processing 8, 490–503 (1999)zbMATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Malik, J., Belongie, S., Leung, T., Shi, J.: Contour and texture analysis for image segmentation. Int. J. Computer Vision 43, 7–27 (2001)zbMATHCrossRefGoogle Scholar
  11. 11.
    Geman, S., Geman, D.: Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Trans. on Pattern Analysis and Machine Intelligence 6, 721–741 (1984)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Andrew Blake
    • 1
  • Carsten Rother
    • 1
  • M. Brown
    • 1
  • Patrick Perez
    • 1
  • Philip Torr
    • 1
  1. 1.Microsoft Research Cambridge UKCambridgeUK

Personalised recommendations