Abstract
We present an active learning framework for image segmentation with user interaction. Our system uses a sparse Gaussian Process classifier (GPC) trained on manually labeled image pixels (user scribbles) and refined in every active learning round. As a special feature, our method uses a very efficient online update rule to compute the class predictions in every round. The final segmentation of the image is computed via convex optimization. Results on a standard benchmark data set show that our algorithm is better than a recent state-of-the-art method. We also show that the queries made by the algorithm are more informative compared to randomly increasing the training data, and that our online version is much faster than the standard offline GPC inference.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
These can be either RGB pixel values or a combination of image coordinates and RGB values of the pixels. In our implementation, we use the latter, because it also provides locality information about background and foreground.
References
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. Trans. Patt. Anal. Mach. Intell. 23(11), 1222–1239 (2001)
Csató, L., Opper, M.: Sparse on-line gaussian processes. Neural Comput. 14(3), 641–668 (2002)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. Int. J. Comput. Vis. 59(2), 167–181 (2004)
Kapoor, A., Grauman, K., Urtasun, R., Darrell, T.: Gaussian processes for object categorization. Int. J. Comput. Vis. 88(2), 169–188 (2010)
Lawrence, N., Seeger, M., Herbrich, R.: Fast sparse gaussian process methods: the informative vector machine. Adv. Neural Inf. Process. Syst. 15, 609–616 (2002)
Lawrence, N.D., Platt, J.C., Jordan, M.I.: Extensions of the informative vector machine. In: Winkler, J.R., Niranjan, M., Lawrence, N.D. (eds.) Deterministic and Statistical Methods in Machine Learning. LNCS (LNAI), vol. 3635, pp. 56–87. Springer, Heidelberg (2005)
Lombaert, H., Sun, Y., Grady, L., Xu, C.: A multilevel banded graph cuts method for fast image segmentation. In: International Conference on Computer Vision (ICCV), pp. 259–265 (2005)
Nieuwenhuis, C., Cremers, D.: Spatially varying color distributions for interactive multi-label segmentation. Trans. Patt. Anal. Mach. Intell. 35(5), 1234–1247 (2013)
Nikolova, M., Esedoglu, S., Chan, T.F.: Algorithms for finding global minimizers of image segmentation and denoising models. SIAM J. Appl. Math. 66(5), 1632–1648 (2006)
Paul, R., Triebel, R., Rus, D., Newman, P.: Semantic categorization of outdoor scenes with uncertainty estimates using multi-class Gaussian process classification. In: Proceedings of the International Conference on Intelligent Robots and Systems (IROS) (2012)
Pock, T., Cremers, D., Bischof, H., Chambolle, A.: An algorithm for minimizing the piecewise smooth mumford-shah functional. In: International Conference on Computer Vision (ICCV) (2009)
Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)
Rother, C., Kolmogorov, V., Blake, A.: Grabcut: Interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. (TOG) 23(3), 309–314 (2004)
Santner, J., Pock, T., Bischof, H.: Interactive multi-label segmentation. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part I. LNCS, vol. 6492, pp. 397–410. Springer, Heidelberg (2011)
Triebel, R., Grimmett, H., Paul, R., Posner, I.: Driven learning for driving: how introspection improves semantic mapping. In: Proceedings of International Symposium on Robotics Research (ISRR) (2013)
Unger, M., Pock, T., Trobin, W., Cremers, D., Bischof, H.: TVSeg - interactive total variation based image segmentation. In: British Machine Vision Conference (2008)
Vezhnevets, A., Buhmann, E.J., Ferrari, V.: Active learning for semantic segmentation with expected change. In: Conference on Computer Vision and Pattern Recognition (2012)
Wang, D., Yan, C., Shan, S., Chen, X.: Active learning for interactive segmentation with expected confidence change. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part I. LNCS, vol. 7724, pp. 790–802. Springer, Heidelberg (2013)
Acknowledgment
This work was partly funded by the EU project SPENCER (ICT-2011-600877).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Triebel, R., Stühmer, J., Souiai, M., Cremers, D. (2014). Active Online Learning for Interactive Segmentation Using Sparse Gaussian Processes. In: Jiang, X., Hornegger, J., Koch, R. (eds) Pattern Recognition. GCPR 2014. Lecture Notes in Computer Science(), vol 8753. Springer, Cham. https://doi.org/10.1007/978-3-319-11752-2_53
Download citation
DOI: https://doi.org/10.1007/978-3-319-11752-2_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11751-5
Online ISBN: 978-3-319-11752-2
eBook Packages: Computer ScienceComputer Science (R0)