DanskDTU.dkIndexContactPhone bookInternal PagesDTU Alumni
English > Research > Image Analysis & Computer Graphics > Publications
Research areas
Algorithms and Logic
Cognitive Systems
Data Analysis
Dynamical Systems
Embedded Systems Engineering
Image Analysis & Computer Graphics
Research
IMM-Image Calendar
People
Publications
Teaching
Language-Based Technology
Mathematical Statistics
Scientific Computing
Software Engineering
Research centers
Publications
Title: Segmentation by Large Scale Hypothesis Testing - Segmentation as Outlier Detection
Type: Article in proceedingsArticle in proceedings
Participant(s):
Author:  Darkner, Sune (Cwisno: 21131)
Technical University of Denmark
Email:

Author:  Dahl, Anders Lindbjerg (Cwisno: 32847)
Technical University of Denmark
Email:

Author:  Larsen, Rasmus (Cwisno: 1431)
Technical University of Denmark
Email:

Author:  Skimminge, Arnold Jesper Møller (Cwisno: 33893)
Technical University of Denmark
Email:

Forfatter:  Garde, Ellen
Technical University of Denmark

Forfatter:  Waldemar, Gunhild
Technical University of Denmark
Abstract: We propose a novel and efficient way of performing local image segmentation. For many applications a threshold of pixel intensities is sufficient but determine the appropriate threshold value can be difficult. 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 background distribution we characterize the segment of interest as a set of outliers with a certain probability based on the estimated densities thus with what certainty the segmented object is not a part of the background. 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 handle 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 the methods corpus callosum segmentation to manual segmentation an average dice score of 0.86 is obtained over 40 images.
Published: part of: Proceedings of the International Conference on Computer Vision Theory and Applications, 2010,
Presented at: 5th International Conference on Computer Vision Theory and Applications, Angers
See the publication in DTU Orbit See the publication in DTU Orbit

Top
MatematiktorvetDTU - Building 303BDK-2800 Kgs. LyngbyTel +45 4525 3031EAN 5798000428515
Cookies