Efficient segmentation by sparse pixel classification
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Efficient segmentation by sparse pixel classification. / Dam, Erik Bjørnager; Loog, Marco.
In: IEEE Transactions on Medical Imaging, Vol. 27, No. 10, 2008, p. 1525-1534.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
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