Abstract
We present a novel algorithm for unsupervised segmentation of natural images that harnesses the principle of minimum description length (MDL). Our method is based on observations that a homogeneously textured region of a natural image can be well modeled by a Gaussian distribution and the region boundary can be effectively coded by an adaptive chain code. The optimal segmentation of an image is the one that gives the shortest coding length for encoding all textures and boundaries in the image, and is obtained via an agglomerative clustering process applied to a hierarchy of decreasing window sizes. The optimal segmentation also provides an accurate estimate of the overall coding length and hence the true entropy of the image. Our algorithm achieves state-of-the-art results on the Berkeley Segmentation Dataset compared to other popular methods.
This work is partially supported by NSF CAREER IIS-0347456, ONR YIP N00014-05-1-0633, and ARO MURI W911NF-06-1-0076.
This is a preview of subscription content, log in via an institution to check access.
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
Leclerc, Y.: Constructing Simple Stable Descriptions for Image Partitioning. IJCV 3, 73–102 (1989)
Shi, J., Malik, J.: Normalized cuts and image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR (1997)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. International Journal of Computer Vision (IJCV) 59(2), 167–181 (2004)
Comanicu, D., Meer, P.: Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 24, 603–619 (2002)
Fua, P., Hanson, A.J.: An Optimization Framework for Feature Extraction. Machine Vision and Applications 4, 59–87 (1991)
Arbelaez, P.: Boundary extraction in natural images using ultrametric contour maps. In: Workshop on Perceptual Organization in Computer Vision (2006)
Ren, X., Fowlkes, C., Malik, J.: Learning probabilistic models for contour completion in natural images. IJCV 77, 47–63 (2008)
Tu, Z., Zhu, S.: Image segmentation by data-driven Markov Chain Monte Carlo. PAMI 24(5), 657–673 (2002)
Kim, J., Fisher, J., Yezzi, A., Cetin, M., Willsky, A.: A nonparametric statistical method for image segmentation using information theory and curve evolution. PAMI 14(10), 1486–1502 (2005)
Yu, S.: Segmentation induced by scale invariance. In: CVPR (2005)
Ren, X., Fowlkes, C., Malik, J.: Scale-invariant contour completion using condition random fields. In: ICCV (2005)
Yang, A., Wright, J., Ma, Y., Sastry, S.: Unsupervised segmentation of natural images via lossy data compression. Computer Vision and Image Understanding 110(2), 212–225 (2008)
Ma, Y., Derksen, H., Hong, W., Wright, J.: Segmentation of multivariate mixed data via lossy coding and compression. PAMI 29(9), 1546–1562 (2007)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics. In: ICCV (2001)
Levina, E., Bickel, P.J.: Texture synthesis and non-parametric resampling of random fields. Annals of Statistics 34(4), 1751–1773 (2006)
Efros, A., Leung, T.: Texture synthesis by non-parametric sampling. In: ICCV (1999)
Liu, Y.K., Zalik, B.: Efficient chain code with Huffman coding. Pattern Recognition 38(4), 553–557 (2005)
Mori, G., Ren, X., Efros, A., Malik, J.: Recovering human body configurations: combining segmentation and recognition. In: CVPR (2004)
Rao, S., Mobahi, H., Yang, A., Sastry, S., Ma, Y.: Natural image segmentation with adaptive texture and boundary encoding. Technical Report UILU-ENG-09-2211 DC-244, UIUC (2009)
Rand, W.M.: Objective criteria for the evaluation of clustering methods. Journal of the American Statistical Association 66(336), 846–850 (1971)
Meila, M.: Comparing clusterings: An axiomatic view. In: Proceedings of the International Conference on Machine Learning (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rao, S.R., Mobahi, H., Yang, A.Y., Sastry, S.S., Ma, Y. (2010). Natural Image Segmentation with Adaptive Texture and Boundary Encoding. In: Zha, H., Taniguchi, Ri., Maybank, S. (eds) Computer Vision – ACCV 2009. ACCV 2009. Lecture Notes in Computer Science, vol 5994. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12307-8_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-12307-8_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12306-1
Online ISBN: 978-3-642-12307-8
eBook Packages: Computer ScienceComputer Science (R0)