Abstract
We propose a novel approach for improving level set segmentation methods by embedding the potential functions from a discriminatively trained conditional random field (CRF) into a level set energy function. The CRF terms can be efficiently estimated and lead to both discriminative local potentials and edge regularizers that take into account interactions among the labels. Unlike discrete CRFs, the use of a continuous level set framework allows the natural use of flexible continuous regularizers such as shape priors. We show promising experimental results for the method on two difficult medical image segmentation tasks.
Keywords
CRFSConditional random fieldDiscriminative modelEmbeddingComputer scienceArtificial intelligencePattern recognition (psychology)SegmentationSet (abstract data type)Prior probabilityLevel set (data structures)Image segmentationEnergy (signal processing)Random fieldImage (mathematics)MathematicsStatistics
Affiliated Institutions
Related Publications
Deep convolutional neural fields for depth estimation from a single image
We consider the problem of depth estimation from a sin- gle monocular image in this work. It is a challenging task as no reliable depth cues are available, e.g., stereo corre- s...
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation
Recent advances in semantic image segmentation have mostly been achieved by training deep convolutional neural networks (CNNs). We show how to improve semantic segmentation thro...
SCARF: A Segmental CRF Speech Recognition System
We propose a theoretical framework for doing speech recognition with segmental conditional random fields, and describe the implemenation of a toolkit for experimenting with thes...
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical ...
Harmony potentials for joint classification and segmentation
Hierarchical conditional random fields have been successfully applied to object segmentation. One reason is their ability to incorporate contextual information at different scal...
Publication Info
- Year
- 2009
- Type
- article
- Volume
- b 36
- Pages
- 328-335
- Citations
- 20
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
20
OpenAlex
Cite This
Dana Cobzaş,
Mark Schmidt
(2009).
Increased discrimination in level set methods with embedded conditional random fields.
2009 IEEE Conference on Computer Vision and Pattern Recognition
, b 36
, 328-335.
https://doi.org/10.1109/cvpr.2009.5206812
Identifiers
- DOI
- 10.1109/cvpr.2009.5206812