Multi-class image segmentation using conditional random fields and global classification

Authors:
Nils Plath;Marc Toussaint;Shinichi Nakajima
Affiliations:
TU Berlin, Berlin, Germany;TU Berlin, Berlin, Germany;Nikon Corporation, Shinagawa-ku, Tokyo, Japan
Venue:
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
Year:
2009

Citing 11
Cited 6

Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Efficient Graph-Based Image Segmentation

International Journal of Computer Vision
Large Margin Methods for Structured and Interdependent Output Variables

The Journal of Machine Learning Research
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study

International Journal of Computer Vision
Large Scale Multiple Kernel Learning

The Journal of Machine Learning Research
Figure-ground segmentation using a hierarchical conditional random field

CRV '07 Proceedings of the Fourth Canadian Conference on Computer and Robot Vision
Representing shape with a spatial pyramid kernel

Proceedings of the 6th ACM international conference on Image and video retrieval
Image modeling using tree structured conditional random fields

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Sampling strategies for bag-of-features image classification

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV

On parameter learning in CRF-based approaches to object class image segmentation

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part VI
Detection of gad-enhancing lesions in multiple sclerosis using conditional random fields

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part III
From local features to global shape constraints: heterogeneous matching scheme for recognizing objects under serious background clutter

ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part IV
A Bayesian approach for scene interpretation with integrated hierarchical structure

DAGM'11 Proceedings of the 33rd international conference on Pattern recognition
Harmony Potentials

International Journal of Computer Vision
Efficient semantic image segmentation with multi-class ranking prior

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentation which combines two methods for this integration: a Conditional Random Field (CRF) which couples to local image features and an image classification method which considers global features. The CRF follows the approach of Reynolds & Murphy (2007) and is based on an unsupervised multi scale pre-segmentation of the image into patches, where patch labels correspond to the random variables of the CRF. The output of the classifier is used to constraint this CRF. We demonstrate and compare the approach on a standard semantic segmentation data set.