Image thresholding by indicator kriging

Wonho Oh; W. Brent Lindquist

doi:10.1109/34.777370

Image thresholding by indicator kriging

Wonho Oh, W. Brent Lindquist

Mathematics and Statistics

Research output: Contribution to journal › Article › peer-review

356 Scopus citations

Abstract

We consider the problem of segmenting a digitized image consisting of two univariate populations. Assume a priori knowledge allows incomplete assignment of voxels in the image, in the sense that a fraction of the voxels can be identified as belonging to population ∏₀, a second fraction to ∏₁, and the remaining fraction have no a priori identification. Based upon estimates of the short length scale spatial covariance of the image, we develop a method utilizing indicator kriging to complete the image segmentation.

Original language	English
Pages (from-to)	590-602
Number of pages	13
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	21
Issue number	7
DOIs	https://doi.org/10.1109/34.777370
State	Published - 1999

Access to Document

10.1109/34.777370

Cite this

@article{931ea2ad2fbc44b1b19a12e8ecf41dbc,

title = "Image thresholding by indicator kriging",

abstract = "We consider the problem of segmenting a digitized image consisting of two univariate populations. Assume a priori knowledge allows incomplete assignment of voxels in the image, in the sense that a fraction of the voxels can be identified as belonging to population ∏0, a second fraction to ∏1, and the remaining fraction have no a priori identification. Based upon estimates of the short length scale spatial covariance of the image, we develop a method utilizing indicator kriging to complete the image segmentation.",

author = "Wonho Oh and {Brent Lindquist}, W.",

note = "Funding Information: This work was supported by the Geosciences program of",

year = "1999",

doi = "10.1109/34.777370",

language = "English",

volume = "21",

pages = "590--602",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

number = "7",

}

TY - JOUR

T1 - Image thresholding by indicator kriging

AU - Oh, Wonho

AU - Brent Lindquist, W.

N1 - Funding Information: This work was supported by the Geosciences program of

PY - 1999

Y1 - 1999

N2 - We consider the problem of segmenting a digitized image consisting of two univariate populations. Assume a priori knowledge allows incomplete assignment of voxels in the image, in the sense that a fraction of the voxels can be identified as belonging to population ∏0, a second fraction to ∏1, and the remaining fraction have no a priori identification. Based upon estimates of the short length scale spatial covariance of the image, we develop a method utilizing indicator kriging to complete the image segmentation.

AB - We consider the problem of segmenting a digitized image consisting of two univariate populations. Assume a priori knowledge allows incomplete assignment of voxels in the image, in the sense that a fraction of the voxels can be identified as belonging to population ∏0, a second fraction to ∏1, and the remaining fraction have no a priori identification. Based upon estimates of the short length scale spatial covariance of the image, we develop a method utilizing indicator kriging to complete the image segmentation.

UR - http://www.scopus.com/inward/record.url?scp=0032679190&partnerID=8YFLogxK

U2 - 10.1109/34.777370

DO - 10.1109/34.777370

M3 - Article

AN - SCOPUS:0032679190

SN - 0162-8828

VL - 21

SP - 590

EP - 602

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 7

ER -

Image thresholding by indicator kriging

Abstract

Access to Document

Other files and links

Fingerprint

Cite this