Back to Search
Start Over
Conditional Random Fields for Image Labeling
- Source :
- Mathematical Problems in Engineering, Vol 2016 (2016)
- Publication Year :
- 2016
- Publisher :
- Hindawi Limited, 2016.
-
Abstract
- With the rapid development and application of CRFs (Conditional Random Fields) in computer vision, many researchers have made some outstanding progress in this domain because CRFs solve the classical version of the label bias problem with respect to MEMMs (maximum entropy Markov models) and HMMs (hidden Markov models). This paper reviews the research development and status of object recognition with CRFs and especially introduces two main discrete optimization methods for image labeling with CRFs: graph cut and mean field approximation. This paper describes graph cut briefly while it introduces mean field approximation more detailedly which has a substantial speed of inference and is researched popularly in recent years.
- Subjects :
- Conditional random field
Computer Science::Machine Learning
Theoretical computer science
General Mathematics
Inference
02 engineering and technology
Statistics::Machine Learning
Discrete optimization
Cut
0202 electrical engineering, electronic engineering, information engineering
Hidden Markov model
CRFS
Mathematics
business.industry
Maximum-entropy Markov model
lcsh:Mathematics
General Engineering
Cognitive neuroscience of visual object recognition
020207 software engineering
Pattern recognition
lcsh:QA1-939
ComputingMethodologies_PATTERNRECOGNITION
lcsh:TA1-2040
020201 artificial intelligence & image processing
Artificial intelligence
business
lcsh:Engineering (General). Civil engineering (General)
Subjects
Details
- Language :
- English
- ISSN :
- 15635147
- Volume :
- 2016
- Database :
- OpenAIRE
- Journal :
- Mathematical Problems in Engineering
- Accession number :
- edsair.doi.dedup.....1f419522cf49b5069ff2a4d656a04edd