Abstract
In this paper we describe a new technique for general purpose interactive segmentation of N-dimensional images. The user marks certain pixels as "object" or "background" to provide hard constraints for segmentation. Additional soft constraints incorporate both boundary and region information. Graph cuts are used to find the globally optimal segmentation of the N-dimensional image. The obtained solution gives the best balance of boundary and region properties among all segmentations satisfying the constraints. The topology of our segmentation is unrestricted and both "object" and "background" segments may consist of several isolated parts. Some experimental results are presented in the context of photo/video editing and medical image segmentation. We also demonstrate an interesting Gestalt example. A fast implementation of our segmentation method is possible via a new max-flow algorithm.
Keywords
SegmentationSegmentation-based object categorizationScale-space segmentationImage segmentationMinimum spanning tree-based segmentationComputer scienceCutArtificial intelligenceComputer visionPixelBoundary (topology)Gestalt psychologyRegion growingGraphObject (grammar)Range segmentationContext (archaeology)Pattern recognition (psychology)MathematicsTheoretical computer scienceGeography
Affiliated Institutions
Related Publications
Region competition: unifying snakes, region growing, energy/Bayes/MDL for multi-band image segmentation
We present a novel statistical and variational approach to image segmentation based on a new algorithm named region competition. This algorithm is derived by minimizing a genera...
Normalized cuts and image segmentation
We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach...
Caltech-256 Object Category Dataset
We introduce a challenging set of 256 object categories containing a total of 30607 images. The original Caltech-101 [1] was collected by choosing a set of object categories, do...
A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semi-supervised manner: the model is learnt from example images ...
Snakes, shapes, and gradient vector flow
Snakes, or active contours, are used extensively in computer vision and image processing applications, particularly to locate object boundaries. Problems associated with initial...
Publication Info
- Year
- 2002
- Type
- article
- Volume
- 1
- Pages
- 105-112
- Citations
- 3633
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
3633
OpenAlex
Cite This
Yuri Boykov,
Marie‐Pierre Jolly
(2002).
Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images.
, 1
, 105-112.
https://doi.org/10.1109/iccv.2001.937505
Identifiers
- DOI
- 10.1109/iccv.2001.937505