Abstract
This paper provides a novel method for co-segmentation, namely simultaneously segmenting multiple images with same foreground and distinct backgrounds. Our contribution primarily lies in four-folds. First, image pairs are typically captured under different imaging conditions, which makes the color distribution of desired object shift greatly, hence it brings challenges to color-based co-segmentation. Here we propose a robust regression method to minimize color variances between corresponding image regions. Secondly, although having been intensively discussed, the exact meaning of the term ”co-segmentation” is rather vague and importance of image background is previously neglected, this motivate us to provide a novel, clear and comprehensive definition for co-segmentation. Thirdly, it is an involved issue that specific regions tend to be categorized as foreground, so we introduce ”risk term” to differentiate colors, which has not been discussed before in the literatures to our best knowledge. Lastly and most importantly, unlike conventional linear global terms in MRFs, we propose a sum-of-squared-difference (SSD) based global constraint and deduce its equivalent quadratic form which takes into account the pairwise relations in feature space. Reasonable assumptions are made and global optimal could be efficiently obtained via alternating Graph Cuts.
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
Yu, S.X., Shi, J.: Multiclass spectral clustering. In: ICCV, pp. 313–319 (2003)
Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images. In: ICCV, pp. 105–112 (2001)
Rother, C., Kolmogorov, V., Blake, A.: ”grabcut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23(3), 309–314 (2004)
Li, Y., Sun, J., Tang, C.K., Shum, H.Y.: Lazy snapping. ACM Trans. Graph. 23(3), 303–308 (2004)
Wang, J., Cohen, M.F.: An iterative optimization approach for unified image segmentation and matting. In: ICCV, pp. 936–943 (2005)
Kolmogorov, V., Criminisi, A., Blake, A., Cross, G., Rother, C.: Bi-layer segmentation of binocular stereo video. CVPR (2), 407–414 (2005)
Sun, J., Kang, S.-B., Xu, Z., Tang, X., Shum, H.Y.: Flash cut: Foreground extraction with flash/no-falsh image pairs. In: CVPR (2007)
Rother, C., Minka, T.P., Blake, A., Kolmogorov, V.: Cosegmentation of image pairs by histogram matching - incorporating a global constraint into mrfs. CVPR (1), 993–1000 (2006)
Narasimhan, M., Bilmes, J.: A submodular-supermodular procedure with applications to discriminative structure learning. In: UAI, pp. 404–441. AUAI Press (2005)
van de Weijer, J., Gevers, T.: Boosting saliency in color image features. CVPR (1), 365–372 (2005)
Weiss, Y.: Deriving intrinsic images from image sequences. In: ICCV, pp. 68–75 (2001)
Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV, pp. 1150–1157 (1999)
Hastie, T., Tibshirani, R., Friedman, J.H.: The Elements of Statistical Learning. Springer, Heidelberg (2001)
Kolmogorov, V., Zabih, R.: What energy functions can be minimized via graph cuts? In: ECCV (3), pp. 65–81 (2002)
Barbu, A., Zhu, S.C.: Generalizing swendsen-wang to sampling arbitrary posterior probabilities. IEEE Trans. Pattern Anal. Mach. Intell. 27(8), 1239–1253 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mu, Y., Zhou, B. (2007). Co-segmentation of Image Pairs with Quadratic Global Constraint in MRFs. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds) Computer Vision – ACCV 2007. ACCV 2007. Lecture Notes in Computer Science, vol 4844. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76390-1_82
Download citation
DOI: https://doi.org/10.1007/978-3-540-76390-1_82
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76389-5
Online ISBN: 978-3-540-76390-1
eBook Packages: Computer ScienceComputer Science (R0)