Globally optimal regions and boundaries
- 1 January 1999
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 904-910 vol.2
- https://doi.org/10.1109/iccv.1999.790318
Abstract
We propose a new form of energy functional for the segmentation of regions in images, and an efficient method for finding its global optima. The energy can have contributions from both the region and its boundary, thus combining the best features of region- and boundary-based approaches to segmentation. By transforming the region energy into a boundary energy, we can treat both contributions on an equal footing, and solve the global optimization problem as a minimum mean weight cycle problem on a directed graph. The simple, polynomial-time algorithm requires no initialization and is highly parallelizable.Keywords
This publication has 16 references indexed in Scilit:
- Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and SalienceNeural Computation, 1997
- Inferring global pereeptual contours from local featuresInternational Journal of Computer Vision, 1996
- Dynamic programming for detecting, tracking, and matching deformable contoursIeee Transactions On Pattern Analysis and Machine Intelligence, 1995
- A measure of closureVision Research, 1994
- A closed curve is much more than an incomplete one: effect of closure in figure-ground segmentation.Proceedings of the National Academy of Sciences, 1993
- The effect of contour closure on the rapid discrimination of two-dimensional shapesVision Research, 1993
- Radial projection: an efficient update rule for relaxation labelingIeee Transactions On Pattern Analysis and Machine Intelligence, 1989
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988
- A characterization of the minimum cycle mean in a digraphDiscrete Mathematics, 1978
- On the optimal detection of curves in noisy picturesCommunications of the ACM, 1971