Abstract
Natural scenes consist of a wide variety of stochastic patterns. While many patterns are represented well by statistical models in two dimensional regions as most image segmentation work assume, some other patterns are fundamentally one dimensional and thus cause major problems in segmentation. We call the former region processes and the latter curve processes. In this paper, we propose a stochastic algorithm for parsing an image into a number of region and curve processes. The paper makes the following contributions to the literature. Firstly, it presents a generative rope model for curve processes in the form of Hidden Markov Model (HMM). The hidden layer is a Markov chain with each element being an image base selected from an over-complete basis, such as Difference of Gaussians (DOG) or Difference of Offset Gaussians (DOOG) at various scales and orientations. The rope model accounts for the geometric smoothness and photometric coherence of the curve processes. Secondly, it integrates both 2D region models, such as textures, splines etc with 1D curve models under the Bayes framework. Because both region and curve models are generative, they compete to explain input images in a layered representation. Thirdly, it achieves global optimization by effective Markov chain Monte Carlo methods in the sense of maximizing a posterior probability. The Markov chain consists of reversible jumps and diffusions driven by bottom up information. The algorithm is applied to real images with satisfactory results. We verify the results through random synthesis and compare them against segmentations with region processes only.
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.
Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
J. August and S.W. Zucker. A generative model of curve images with a completely-characterized non-gaussian joint distribution. In Proc. of Workshop on Stat. and Comp. Theories of Vis., July, 2001.
M. Isard and A. Blake. Contour tracking by stochastic propagation of conditional density. Proc. ECCV, 1996.
T.F. Cootes, D. Cooper, C.J. Taylor and J. Graham. Active shape models-their training and application. Computer Vision and Image Understanding, vol. 61, no. 1, Jan. pages 38–59, 1995.
U. Grenander and M. I. Miller. Representation of knowledge in complex systems. J. R. Stat. Soc., B, vol 56, 549–603, 1994
P. J. Green. Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika, vol. 82, 711–732, 1995.
J. Malik, S. Belongie, T. Leung, and J. Shi. Contour and texture analysis for image segmentation. IJCV, vo. 43, no. 1, June 2001.
S.G. Mallat and Z. Zhang. Matching pursuits with time-frequency dictionaries. IEEE Tranc. on Signal Processing, vol. 41, no. 12, Dec. 1993.
D. Mumford. Algebraic geometry and its applications, chaper elastic and computer vision, pp. 491–506. Springer-Verlag, 1994.
B. A. Olshausen and D. J. Field. Sparse coding with an overcomplete basis set: a strategy employed by v1?. Vision Res., vol. 37, no. 23 3311–25 1997.
M. Kass, A. Witkin and D. Terzopoulos. Snakes: active contour models. IJCV, 1, 1988.
Z. Tu, S.C. Zhu., and H.Y. Shum. Image segmentation by data driven markov chain monte carlo. Proc. ICCV, 2001.
S. C. Zhu and A. L. Yuille. Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation. IEEE Trans. PAMI vol. 18, No. 9, 1996.
S.C. Zhu. Embedding gestalt laws in markov random fields-a theory for shape modeling and perceptual organization. PAMI, vol. 21, no. 11, Nov. 1999.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tu, Z., Zhu, SC. (2002). Parsing Images into Region and Curve Processes. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds) Computer Vision — ECCV 2002. ECCV 2002. Lecture Notes in Computer Science, vol 2352. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-47977-5_26
Download citation
DOI: https://doi.org/10.1007/3-540-47977-5_26
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43746-8
Online ISBN: 978-3-540-47977-2
eBook Packages: Springer Book Archive