Bayesian Object Detection through Level Curves Selection
Bayesian statistical theory is a convenient way of taking a priori information into consideration when inference is made from images. In Bayesian image detection, the a priori distribution should capture the knowledge about objects. Taking inspiration from , we design a prior density that penalizes the area of homogeneous parts in images. The detection problem is further formulated as the estimation of the set of curves that maximizes the posterior distribution. In this paper, we explore a posterior distribution model for which its maximal mode is given by a subset of level curves, that is the boundaries of image level sets. For the completeness of the paper, we present a stepwise greedy algorithm for computing partitions with connected components.
KeywordsImage Segmentation Level Line Active Contour Model Homogeneous Part Connected Component Label
Unable to display preview. Download preview PDF.
- 1.L. Alvarez, Y. Gousseau, and J.M. Morel. Scales in natural images and a consequence on their bounded variation. In Int. Conf. on Scale-Space Theories Comp. Vis., pages 247–258, Kerkyra, Greece, September 1999.Google Scholar
- 2.A. Blake and A. Zisserman. Visual Reconstruction. MIT Press, Cambridge, Mass, 1987.Google Scholar
- 4.T. Chan and L. Vese. Active contour model without edges. In Int. Conf. on Scale-Space Theories Comp. Vis., pages 141–151, Kerkyra, Greece, September 1999.Google Scholar
- 7.J. Froment. Perceptible level lines and isoperimetric ratio. In Int. Conf. on Image Processing, Vancouver, Canada, 2000.Google Scholar
- 12.M. Kass, A. Witkin, and D. Terzopoulos. Snakes: active contour models. Int J. Computer Vision, 12(1):321–331, 1987.Google Scholar
- 13.C. Kervrann, M. Hoebeke, and A. Trubuil. Level lines as global minimizers of energy functionals in image segmentation. In Euro. Conf. on Comp. Vis., pages 241–256, Dublin, Ireland, June 2000.Google Scholar
- 16.J. M∅ller and R.P. Waagepertersen. Markov connected component fields. Adv. in Applied Probability, pages 1–35, 1998.Google Scholar
- 17.J.M. Morel and S. Solimini. Variational methods in image segmentation. Birkhauser, 1994.Google Scholar
- 20.N. Paragios and R. Deriche. Coupled geodesic active regions for image segmentation: a level set approach. In Euro. Conf. on Comp. Vis., pages 224–240, Dublin, Ireland, June 2000.Google Scholar
- 22.J. Sethian. Level Sets Methods: Evolving Interfaces in Geometry, Fluid Mechanics, Computer Vision, and Material Science. Cambridges University Press, 1996.Google Scholar
- 24.A. Yezzi, A. Tsai, and A. Willsky. A statistical approach to snakes for bimodal and trimodal imagery. In Int. Conf. on Comp. Vis., pages 898–903, Kerkyra, Greece, September 1999.Google Scholar