A systematic performance evaluation of interactive image segmentation methods based on simulated user interaction

Emmanouil Moschidis; Jim Graham

doi:10.1109/ISBI.2010.5490139

A systematic performance evaluation of interactive image segmentation methods based on simulated user interaction

Emmanouil Moschidis, Jim Graham

Research output: Contribution to conference › Poster

Abstract

In this paper we report on the results of a systematic performance evaluation of three efficient image segmentation algorithms, namely Graph-Cuts, Random-Walker and Grow-Cut. The evaluation focuses on their function as the computational part of an interactive segmentation system. The implications caused by the human involvement in the overall process are avoided by simulating two different patterns of user interaction. The methods are evaluated with respect to accuracy, precision, efficiency and parameter sensitivity on three dimensional medical images. The results provide useful insight regarding the algorithmic performance of the selected techniques and the effect of the identified patterns of user interaction on the segmentation outcome. © 2010 IEEE.

Original language	English
Pages	928-931
Number of pages	3
DOIs	https://doi.org/10.1109/ISBI.2010.5490139
Publication status	Published - 2010
Event	7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 - Rotterdam Duration: 1 Jul 2010 → …

Conference

Conference	7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010
City	Rotterdam
Period	1/07/10 → …

Keywords

3-D medical images
Graph-Cuts
Grow-cut
Interactive image segmentation
Performance evaluation
Random-Walker
Simulated user interaction

Access to Document

10.1109/ISBI.2010.5490139

Cite this

@conference{39adf39d6c854a7f92e0dea70ff4e334,

title = "A systematic performance evaluation of interactive image segmentation methods based on simulated user interaction",

abstract = "In this paper we report on the results of a systematic performance evaluation of three efficient image segmentation algorithms, namely Graph-Cuts, Random-Walker and Grow-Cut. The evaluation focuses on their function as the computational part of an interactive segmentation system. The implications caused by the human involvement in the overall process are avoided by simulating two different patterns of user interaction. The methods are evaluated with respect to accuracy, precision, efficiency and parameter sensitivity on three dimensional medical images. The results provide useful insight regarding the algorithmic performance of the selected techniques and the effect of the identified patterns of user interaction on the segmentation outcome. {\textcopyright} 2010 IEEE.",

keywords = "3-D medical images, Graph-Cuts, Grow-cut, Interactive image segmentation, Performance evaluation, Random-Walker, Simulated user interaction",

author = "Emmanouil Moschidis and Jim Graham",

year = "2010",

doi = "10.1109/ISBI.2010.5490139",

language = "English",

pages = "928--931",

note = "7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010 ; Conference date: 01-07-2010",

}

TY - CONF

T1 - A systematic performance evaluation of interactive image segmentation methods based on simulated user interaction

AU - Moschidis, Emmanouil

AU - Graham, Jim

PY - 2010

Y1 - 2010

N2 - In this paper we report on the results of a systematic performance evaluation of three efficient image segmentation algorithms, namely Graph-Cuts, Random-Walker and Grow-Cut. The evaluation focuses on their function as the computational part of an interactive segmentation system. The implications caused by the human involvement in the overall process are avoided by simulating two different patterns of user interaction. The methods are evaluated with respect to accuracy, precision, efficiency and parameter sensitivity on three dimensional medical images. The results provide useful insight regarding the algorithmic performance of the selected techniques and the effect of the identified patterns of user interaction on the segmentation outcome. © 2010 IEEE.

AB - In this paper we report on the results of a systematic performance evaluation of three efficient image segmentation algorithms, namely Graph-Cuts, Random-Walker and Grow-Cut. The evaluation focuses on their function as the computational part of an interactive segmentation system. The implications caused by the human involvement in the overall process are avoided by simulating two different patterns of user interaction. The methods are evaluated with respect to accuracy, precision, efficiency and parameter sensitivity on three dimensional medical images. The results provide useful insight regarding the algorithmic performance of the selected techniques and the effect of the identified patterns of user interaction on the segmentation outcome. © 2010 IEEE.

KW - 3-D medical images

KW - Graph-Cuts

KW - Grow-cut

KW - Interactive image segmentation

KW - Performance evaluation

KW - Random-Walker

KW - Simulated user interaction

U2 - 10.1109/ISBI.2010.5490139

DO - 10.1109/ISBI.2010.5490139

M3 - Poster

SP - 928

EP - 931

T2 - 7th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2010

Y2 - 1 July 2010

ER -

A systematic performance evaluation of interactive image segmentation methods based on simulated user interaction

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this