Decision boundaries using Bayes factors

The case of cloud masks

F. Murtagh, D. Barreto, J. Marcello

Research output: Contribution to journalLetter

28 Citations (Scopus)

Abstract

We assess the use of an approximation to the Bayes factor for objectively assessing spatial segmentation models. The Bayes factor allows us to automatically determine thresholds, in multidimensional feature space, for such objectives as cloud mask definition. We compare our results with a cloud map currently provided as a data product.

Original languageEnglish
Pages (from-to)2952-2958
Number of pages7
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume41
Issue number12 PART II
DOIs
Publication statusPublished - 1 Dec 2003
Externally publishedYes

Fingerprint

Masks
segmentation
decision
product

Cite this

Murtagh, F. ; Barreto, D. ; Marcello, J. / Decision boundaries using Bayes factors : The case of cloud masks. In: IEEE Transactions on Geoscience and Remote Sensing. 2003 ; Vol. 41, No. 12 PART II. pp. 2952-2958.
@article{75fd547e6ff04b0cbd3b9a3732c91ad6,
title = "Decision boundaries using Bayes factors: The case of cloud masks",
abstract = "We assess the use of an approximation to the Bayes factor for objectively assessing spatial segmentation models. The Bayes factor allows us to automatically determine thresholds, in multidimensional feature space, for such objectives as cloud mask definition. We compare our results with a cloud map currently provided as a data product.",
keywords = "Bayes factor, Bayes information criterion (BIC), Gaussian mixture model, Markov model, Model selection, Multiband image, Potts prior, Principal components analysis, Segmentation",
author = "F. Murtagh and D. Barreto and J. Marcello",
year = "2003",
month = "12",
day = "1",
doi = "10.1109/TGRS.2003.819874",
language = "English",
volume = "41",
pages = "2952--2958",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "12 PART II",

}

Decision boundaries using Bayes factors : The case of cloud masks. / Murtagh, F.; Barreto, D.; Marcello, J.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 41, No. 12 PART II, 01.12.2003, p. 2952-2958.

Research output: Contribution to journalLetter

TY - JOUR

T1 - Decision boundaries using Bayes factors

T2 - The case of cloud masks

AU - Murtagh, F.

AU - Barreto, D.

AU - Marcello, J.

PY - 2003/12/1

Y1 - 2003/12/1

N2 - We assess the use of an approximation to the Bayes factor for objectively assessing spatial segmentation models. The Bayes factor allows us to automatically determine thresholds, in multidimensional feature space, for such objectives as cloud mask definition. We compare our results with a cloud map currently provided as a data product.

AB - We assess the use of an approximation to the Bayes factor for objectively assessing spatial segmentation models. The Bayes factor allows us to automatically determine thresholds, in multidimensional feature space, for such objectives as cloud mask definition. We compare our results with a cloud map currently provided as a data product.

KW - Bayes factor

KW - Bayes information criterion (BIC)

KW - Gaussian mixture model

KW - Markov model

KW - Model selection

KW - Multiband image

KW - Potts prior

KW - Principal components analysis

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=0442279712&partnerID=8YFLogxK

U2 - 10.1109/TGRS.2003.819874

DO - 10.1109/TGRS.2003.819874

M3 - Letter

VL - 41

SP - 2952

EP - 2958

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 12 PART II

ER -