Confidence Based Active Learning for Whole Object Image Segmentation

  • Aiyesha Ma
  • Nilesh Patel
  • Mingkun Li
  • Ishwar K. Sethi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4105)


In selective object segmentation, the goal is to extract the entire object of interest without regards to homogeneous regions or object shape. In this paper we present the selective image segmentation problem as a classification problem, and use active learning to train an image feature classifier to identify the object of interest. Since our formulation of this segmentation problem uses human interaction, active learning is used for training to minimize the training effort needed to segment the object. Results using several images with known ground truth are presented to show the efficacy of our approach for segmenting the object of interest in still images. The approach has potential applications in medical image segmentation and content-based image retrieval among others.


Active Learning Image Segmentation Segmentation Result Ground Truth Data Segmentation Approach 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Swain, C., Chen, T.: Defocus-based image segmentation. In: Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, vol. 1995, pp. 2403–2406 (1995)Google Scholar
  2. 2.
    Harville, M., Gordon, G.G., Woodfill, J.: Foreground segmentation using adaptive mixture models in color and depth. In: IEEE Workshop on Detection and Recognition of Events in Video, pp. 3–11 (2001)Google Scholar
  3. 3.
    Stalling, D., Hege, H.-C.: Intelligent scissors for medical image segmentation. In: Arnolds, B., Müller, H., Saupe, D., Tolxdorff, T. (eds.) Proceedings of 4th Freiburger Workshop Digitale Bildverarbeitung in der Medizin, Freiburg, pp. 32–36 (1996)Google Scholar
  4. 4.
    Rother, C., Kolmogorov, V., Blake, A.: GrabCut: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23, 309–314 (2004)CrossRefGoogle Scholar
  5. 5.
    Blake, A., Rother, C., Brown, M., Perez, P., Torr, P.: Interactive image segmentation using an adaptive GMMRF model. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 428–441. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  6. 6.
    Li, M., Sethi, I.K.: SVM-based classifier design with controlled confidence. In: Proceedings of 17th International Conference on Pattern Recognition (ICPR 2004), Cambridge, UK, vol. 1, pp. 164–167 (2004)Google Scholar
  7. 7.
    Vapnik, V.: Statistical Learning Theory. John Wiley & Sons, Chichester (1998)MATHGoogle Scholar
  8. 8.
    Vapnik, V.: The Nature of Statistical Learning Theory, 2nd edn. Springer, Heidelberg (1999)Google Scholar
  9. 9.
    Burges, C.: A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery 2, 121–167 (1998)CrossRefGoogle Scholar
  10. 10.
    Li, M., Sethi, I.K.: New online learning algorithm with application to image segmentation. In: Proc. Electronic Imaging, Image Processing: Algorithms and Systems IV, vol. 5672, SPIE (2005)Google Scholar
  11. 11.
    Deng, Y., Manjunath, B.S.: Unsupervised segmentation of color-texture regions in images and video. IEEE Transactions on Pattern Analysis and Machine Intelligence 23 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Aiyesha Ma
    • 1
  • Nilesh Patel
    • 2
  • Mingkun Li
    • 3
  • Ishwar K. Sethi
    • 1
  1. 1.Department of Computer Science and EngineeringOakland UniversityRochester
  2. 2.University of Michigan–DearbornDearborn
  3. 3.DOE Joint Genome InstituteWalnut Creek

Personalised recommendations