Efficient segmentation by sparse pixel classification

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Efficient segmentation by sparse pixel classification. / Dam, Erik Bjørnager; Loog, Marco.

I: IEEE Transactions on Medical Imaging, Bind 27, Nr. 10, 2008, s. 1525-1534.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Dam, EB & Loog, M 2008, 'Efficient segmentation by sparse pixel classification', IEEE Transactions on Medical Imaging, bind 27, nr. 10, s. 1525-1534. https://doi.org/10.1109/TMI.2008.923961

APA

Dam, E. B., & Loog, M. (2008). Efficient segmentation by sparse pixel classification. IEEE Transactions on Medical Imaging, 27(10), 1525-1534. https://doi.org/10.1109/TMI.2008.923961

Vancouver

Dam EB, Loog M. Efficient segmentation by sparse pixel classification. IEEE Transactions on Medical Imaging. 2008;27(10):1525-1534. https://doi.org/10.1109/TMI.2008.923961

Author

Dam, Erik Bjørnager ; Loog, Marco. / Efficient segmentation by sparse pixel classification. I: IEEE Transactions on Medical Imaging. 2008 ; Bind 27, Nr. 10. s. 1525-1534.

Bibtex

@article{ff8c73b0f1f111ddbf70000ea68e967b,
title = "Efficient segmentation by sparse pixel classification",
abstract = "Segmentation methods based on pixel classification are powerful but often slow. We introduce two general algorithms, based on sparse classification, for optimizing the computation while still obtaining accurate segmentations. The computational costs of the algorithms are derived, and they are demonstrated on real 3-D magnetic resonance imaging and 2-D radiograph data. We show that each algorithm is optimal for specific tasks, and that both algorithms allow a speedup of one or more orders of magnitude on typical segmentation tasks.",
author = "Dam, {Erik Bj{\o}rnager} and Marco Loog",
note = "Keywords: Algorithms; Artificial Intelligence; Cluster Analysis; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity",
year = "2008",
doi = "10.1109/TMI.2008.923961",
language = "English",
volume = "27",
pages = "1525--1534",
journal = "I E E E Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers",
number = "10",

}

RIS

TY - JOUR

T1 - Efficient segmentation by sparse pixel classification

AU - Dam, Erik Bjørnager

AU - Loog, Marco

N1 - Keywords: Algorithms; Artificial Intelligence; Cluster Analysis; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity

PY - 2008

Y1 - 2008

N2 - Segmentation methods based on pixel classification are powerful but often slow. We introduce two general algorithms, based on sparse classification, for optimizing the computation while still obtaining accurate segmentations. The computational costs of the algorithms are derived, and they are demonstrated on real 3-D magnetic resonance imaging and 2-D radiograph data. We show that each algorithm is optimal for specific tasks, and that both algorithms allow a speedup of one or more orders of magnitude on typical segmentation tasks.

AB - Segmentation methods based on pixel classification are powerful but often slow. We introduce two general algorithms, based on sparse classification, for optimizing the computation while still obtaining accurate segmentations. The computational costs of the algorithms are derived, and they are demonstrated on real 3-D magnetic resonance imaging and 2-D radiograph data. We show that each algorithm is optimal for specific tasks, and that both algorithms allow a speedup of one or more orders of magnitude on typical segmentation tasks.

U2 - 10.1109/TMI.2008.923961

DO - 10.1109/TMI.2008.923961

M3 - Journal article

C2 - 18815104

VL - 27

SP - 1525

EP - 1534

JO - I E E E Transactions on Medical Imaging

JF - I E E E Transactions on Medical Imaging

SN - 0278-0062

IS - 10

ER -

ID: 10117578