Abstract
In this paper, we are interested in the unsupervised co-segmentation of color images. Solving this co-segmentation problem returns usually to optimize an energy function, which evaluates the similarity between the similar foreground objects in the input images. The objective is to evaluate the correspondence of foreground objects that penalizes the dissimilarity between them. To assess this correspondence existing techniques simply compare the histograms in the absence of any information of spatial coherence. The purpose of this paper is to integrate spatial information in order to avoid false detection. Indeed, in addition to the integration of the spatial information thanks to the use of the local entropy during the histogram computing, the main contribution of the proposed technique resides in the fuzzy local-entropy classification which allows to model the ambiguity of a pixel membership to a histogram bin. In particular, this permits to minimize over-segmentation and noise effects on the final co-segmentation results. Recorded results and the comparative study prove the accuracy of the proposed technique for color images co-segmentation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Rother, C., Minka, T., Blake, A., Kolmogorov, V.: Co-segmentation of image pairs by histogram matching: Incorporating a global constraint into MRFs. In: CVPR, New York (2006)
Mukherjee, L., Singh, V., Dyer, C.: Half-integrality based algorithms for cosegmentation of images. In: CVPR, Miami (2009)
Hochbaum, D.S., Singh, V.: An efficient algorithm for co-segmentation. In: International Conference on Computer Vision, Kyoto (2009)
Mukherjee, L., Singh, V., Peng, J.: Scale invariant cosegmentation for image groups. In: International Conference on Computer Vision and Pattern Recognition, Colorado (2011)
Chu, W.-S., Chen, C.-P., Chen, C.-S.: MOMI-Cosegmentation: Simultaneous Segmentation of Multiple Objects among Multiple Images. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part I. LNCS, vol. 6492, pp. 355–368. Springer, Heidelberg (2011)
Joulin, A., Bach, F., Ponce, J.: Discriminative clustering for image co-segmentation. In: CVPR, San Francisco (2010)
Kim, G., Xing, E.P., Fei-Fei, L., Kanade, T.: Distributed co-segmentation via submodular optimization on anisotropic diffusion. In: ICCV, Barcelona (2011)
Chai, Y., Lempitsky, V., Zisserman, A.: BiCoS: A bi-level co-Segmentation method for image classification. In: ICCV, Barcelona (2011)
Kim, G., Xing, P.: On multiple foreground co-segmentation. In: CVPR, Rhode Island (2012)
Batra, D., Kowdle, A., Parikh, D., Luo, J., Chen, T.: Interactively co-segmentating topically related images with intelligent scribble guidance. Computer Vision 93(3), 273–292 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Merdassi, H., Barhoumi, W., Zagrouba, E. (2012). Color Images Co-segmentation Based on Fuzzy Local-Entropy Classification. In: Wang, F.L., Lei, J., Lau, R.W.H., Zhang, J. (eds) Multimedia and Signal Processing. CMSP 2012. Communications in Computer and Information Science, vol 346. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35286-7_31
Download citation
DOI: https://doi.org/10.1007/978-3-642-35286-7_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35285-0
Online ISBN: 978-3-642-35286-7
eBook Packages: Computer ScienceComputer Science (R0)