Abstract
In this chapter, we describe in detail our approach to interactive cosegmentation. We formulate the task as an energy minimization problem across all related images in a group. The energies across images are tied together via a shared appearance model, thus allowing for efficient inference. After describing our formulation, we present an active learning approach that makes efficient use of users’ time. A wide variety of cues are combined to intelligently guide the users’ next scribbles. We then introduce our co-segmentation dataset, The CMU-Cornell iCoseg dataset, the largest of its kind to date. We evaluate our system on this dataset using machine simulations as well as real user-studies.We find that our approach can achieve comparable co-segmentation performance with less user effort.
Keywords
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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bagon, S.: Matlab Wrapper for Graph Cut. http://www.wisdom.weizmann.ac.il/˜bagon (2006).
Batra, D., Kowdle, A., Parikh, D., Tang, K., Chen, T.: Interactive Cosegmentation by Touch.http://amp.ece.cornell.edu/projects/touch-coseg/ (2009).
Batra, D., Kowdle, A., Parikh, D., Luo, J., Chen, T.: Interactively Co-segmentating Topically Related Images with Intelligent Scribble Guidance. International Journal of Computer Vision (2011).
Batra, D., Parikh, D., Kowdle, A., Chen, T., Luo, J.: Seed Image Selection in Interactive Cosegmentation. International Conference on Image Processing (2009).
Batra, D., Sukthankar, R., Chen, T.: Semi-Supervised Clustering via Learnt Codeword Distances. British Machine Vision Conference (2008).
Bouman, C.A.: Cluster: An unsupervised algorithm for modeling Gaussian mixtures. Available from http://www.ece.purdue.edu/\string˜bouman. (1997).
Boykov, Y.Y., Jolly, M.-P.: Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. International Conference on Computer Vision (2001).
Boykov, Y., Kolmogorov, V.: An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision. IEEE Transactions on Pattern Analysis and Machine Intelligence (2004).
Boykov, Y., Veksler, O., Zabih, R.: Efficient Approximate Energy Minimization via Graph Cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence (2001).
Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence (2002).
Criminisi, A., Sharp, T., Blake, A.: GeoS: Geodesic Image Segmentation. European Conference on Computer Vision (2008).
Cui, J., Yang, Q.,Wen, F.,Wu, Q., Zhang, C,. Gool, L.V., Tang, T.: Transductive Object Cutout. IEEE Conference on Computer Vision and Pattern Recognition (2008).
Hochbaum, D.S., Singh, V.: An efficient algorithm for co-segmentation. International Conference on Computer Vision (2009).
Hoiem, D., Efros, A.A., Hebert, M.: Geometric context from a single image. International Conference on Computer Vision (2005).
Kohli, P., Philip, T.H,S: Measuring uncertainty in graph cut solutions. Elsevier Journal on Computer Vision and Image Understanding (2008).
Kolmogorov, V., Zabih, R.: What Energy Functions can be Minimized via Graph Cuts?. IEEE Transactions on Pattern Analysis and Machine Intelligence (2004).
Leung, T., Malik, J.: Contour continuity in region based image segmentation. European Conference on Computer Vision (1998).
Mu, Y.D., Zhou, B.F.: Co-segmentation of Image Pairs with Quadratic Global Constraint in MRFs. Asian Conference on Computer Vision (2007).
Mukherjee, L., Singh, V., Dyer, C.R.: Half-integrality based algorithms for cosegmentation of images. IEEE Conference on Computer Vision and Pattern Recognition (2009).
Oliva, A., Torralba, A.: Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope. International Journal of Computer Vision (2001).
Rother, C., Kolmogorov, V., Blake, A.: GrabCut: interactive foreground extraction using iterated graph cuts. ACM Transactions on Graphics (Proceedings of SIGGRAPH) (2004).
Rother, C., Minka, T., Blake, A., Kolmogorov, V., Cosegmentation of Image Pairs by Histogram Matching - Incorporating a Global Constraint into MRFs (2006)
Seung, H.S., Opper, M., Sompolinsky, H.: Query by committee. Computational Learning Theory (1992).
Schnitman, Y., Caspi, Y., Cohen O.D.. Lischinski, D.: Inducing Semantic Segmentation from an Example. Asian Conference on Computer Vision (2006).
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Science+Business Media, LLC
About this chapter
Cite this chapter
Batra, D., Kowdle, A., Parikh, D., Luo, J., Chen, T. (2011). An Approach to Interactive Co-segmentation. In: Interactive Co-segmentation of Objects in Image Collections. SpringerBriefs in Computer Science. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-1915-0_2
Download citation
DOI: https://doi.org/10.1007/978-1-4614-1915-0_2
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-1914-3
Online ISBN: 978-1-4614-1915-0
eBook Packages: Computer ScienceComputer Science (R0)