Contextual Image Segmentation based on AdaBoost and Markov Random Fields

Ryuei Nishii

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

AdaBoost, one of machine learning algorithms, is employed for classification of land-cover categories of geostatistical data. We assume that the posterior probability is given by the odds ratio due to loss functions. Further, landcover categories are assumed to follow Markov random fields (MRF). Then, we derive a classifier by combining two posteriors based on AdaBoost and MRF through the iterative conditional modes. Our procedure is applied to benchmark data sets provided by IEEE GRSS Data Fusion Committee and shows an excellent performance.

Original languageEnglish
Title of host publicationInternational Geoscience and Remote Sensing Symposium (IGARSS)
Pages3507-3509
Number of pages3
Volume6
Publication statusPublished - 2003
Externally publishedYes
Event2003 IGARSS: Learning From Earth's Shapes and Colours - Toulouse, France
Duration: Jul 21 2003Jul 25 2003

Other

Other2003 IGARSS: Learning From Earth's Shapes and Colours
CountryFrance
CityToulouse
Period7/21/037/25/03

Fingerprint

Adaptive boosting
Image segmentation
segmentation
land cover
Data fusion
Learning algorithms
Learning systems
Classifiers
machine learning
loss

All Science Journal Classification (ASJC) codes

  • Geology
  • Software

Cite this

Nishii, R. (2003). Contextual Image Segmentation based on AdaBoost and Markov Random Fields. In International Geoscience and Remote Sensing Symposium (IGARSS) (Vol. 6, pp. 3507-3509)

Contextual Image Segmentation based on AdaBoost and Markov Random Fields. / Nishii, Ryuei.

International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 6 2003. p. 3507-3509.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nishii, R 2003, Contextual Image Segmentation based on AdaBoost and Markov Random Fields. in International Geoscience and Remote Sensing Symposium (IGARSS). vol. 6, pp. 3507-3509, 2003 IGARSS: Learning From Earth's Shapes and Colours, Toulouse, France, 7/21/03.
Nishii R. Contextual Image Segmentation based on AdaBoost and Markov Random Fields. In International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 6. 2003. p. 3507-3509
Nishii, Ryuei. / Contextual Image Segmentation based on AdaBoost and Markov Random Fields. International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 6 2003. pp. 3507-3509
@inproceedings{f792713d75a341088cfbb0d85e60a1f5,
title = "Contextual Image Segmentation based on AdaBoost and Markov Random Fields",
abstract = "AdaBoost, one of machine learning algorithms, is employed for classification of land-cover categories of geostatistical data. We assume that the posterior probability is given by the odds ratio due to loss functions. Further, landcover categories are assumed to follow Markov random fields (MRF). Then, we derive a classifier by combining two posteriors based on AdaBoost and MRF through the iterative conditional modes. Our procedure is applied to benchmark data sets provided by IEEE GRSS Data Fusion Committee and shows an excellent performance.",
author = "Ryuei Nishii",
year = "2003",
language = "English",
volume = "6",
pages = "3507--3509",
booktitle = "International Geoscience and Remote Sensing Symposium (IGARSS)",

}

TY - GEN

T1 - Contextual Image Segmentation based on AdaBoost and Markov Random Fields

AU - Nishii, Ryuei

PY - 2003

Y1 - 2003

N2 - AdaBoost, one of machine learning algorithms, is employed for classification of land-cover categories of geostatistical data. We assume that the posterior probability is given by the odds ratio due to loss functions. Further, landcover categories are assumed to follow Markov random fields (MRF). Then, we derive a classifier by combining two posteriors based on AdaBoost and MRF through the iterative conditional modes. Our procedure is applied to benchmark data sets provided by IEEE GRSS Data Fusion Committee and shows an excellent performance.

AB - AdaBoost, one of machine learning algorithms, is employed for classification of land-cover categories of geostatistical data. We assume that the posterior probability is given by the odds ratio due to loss functions. Further, landcover categories are assumed to follow Markov random fields (MRF). Then, we derive a classifier by combining two posteriors based on AdaBoost and MRF through the iterative conditional modes. Our procedure is applied to benchmark data sets provided by IEEE GRSS Data Fusion Committee and shows an excellent performance.

UR - http://www.scopus.com/inward/record.url?scp=0242457294&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0242457294&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0242457294

VL - 6

SP - 3507

EP - 3509

BT - International Geoscience and Remote Sensing Symposium (IGARSS)

ER -