loading
Documents

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Sune Darkner 1 ; Anders B. Dahl 1 ; Rasmus Larsen 1 ; Arnold Skimminge 2 ; Ellen Garde 2 and Gunhild Waldemar 2

Affiliations: 1 Technical University of Denmark, Denmark ; 2 Copenhagen University Hospital Hvidovre;Copenhagen University Hospital, Denmark

ISBN: 978-989-674-029-0

Keyword(s): Segmentation, Outlier detection, Large scale hypothesis testing, Locally adjusted threshold.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Image and Video Analysis ; Segmentation and Grouping ; Statistical Approach

Abstract: We propose a novel and efficient way of performing local image segmentation. For many applications a threshold of pixel intensities is sufficient. However, determining the appropriate threshold value poses a challenge. In cases with large global intensity variation the threshold value has to be adapted locally. We propose a method based on large scale hypothesis testing with a consistent method for selecting an appropriate threshold for the given data. By estimating the prominent distribution we characterize the segment of interest as a set of outliers or the distribution it self. Thus, we can calculate a probability based on the estimated densities of outliers actually being outliers using the false discovery rate (FDR). Because the method relies on local information it is very robust to changes in lighting conditions and shadowing effects. The method is applied to endoscopic images of small particles submerged in fluid captured through a microscope and we show how the method can han dle transparent particles with significant glare point. The method generalizes to other problems. This is illustrated by applying the method to camera calibration images and MRI of the midsagittal plane for gray and white matter separation and segmentation of the corpus callosum. Comparing this segmentation method with manual corpus callosum segmentation an average dice score of 0.88 is obtained across 40 images. (More)

PDF ImageFull Text

Download
Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.87.147.184

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Darkner S.; B. Dahl A.; Larsen R.; Skimminge A.; Garde E.; Waldemar G. and (2010). LOCAL SEGMENTATION BY LARGE SCALE HYPOTHESIS TESTING - Segmentation as Outlier Detection.In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-029-0, pages 215-220. DOI: 10.5220/0002845402150220

@conference{visapp10,
author={Sune Darkner and Anders {B. Dahl} and Rasmus Larsen and Arnold Skimminge and Ellen Garde and Gunhild Waldemar},
title={LOCAL SEGMENTATION BY LARGE SCALE HYPOTHESIS TESTING - Segmentation as Outlier Detection},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={215-220},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002845402150220},
isbn={978-989-674-029-0},
}

TY - CONF

JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2010)
TI - LOCAL SEGMENTATION BY LARGE SCALE HYPOTHESIS TESTING - Segmentation as Outlier Detection
SN - 978-989-674-029-0
AU - Darkner, S.
AU - B. Dahl, A.
AU - Larsen, R.
AU - Skimminge, A.
AU - Garde, E.
AU - Waldemar, G.
PY - 2010
SP - 215
EP - 220
DO - 10.5220/0002845402150220

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.