Application of opposition-based reinforcement learning in image segmentation

Farhang Sahba; Hamid R. Tizhoosh; Magdy M.M.A. Salama

doi:10.1109/CIISP.2007.369176

Application of opposition-based reinforcement learning in image segmentation

Farhang Sahba, Hamid R. Tizhoosh, Magdy M.M.A. Salama

Artificial Intelligence and Informatics

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper a method for image segmentation using an opposition-based reinforcement learning scheme is introduced. We use this agent-based approach to optimally find the appropriate local values and segment the object. The agent uses an image and its manually segmented version and takes some actions to change the environment (the quality of segmented image). The agent is provided with a scalar reinforcement signal as reward/punishment. The agent uses this information to explore/exploit the solution space. The values obtained can be used as valuable knowledge to fill the Q-matrix. The results demonstrate potential for applying this new method in the field of medical image segmentation.

Original language	English (US)
Title of host publication	Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007
Pages	246-251
Number of pages	6
DOIs	https://doi.org/10.1109/CIISP.2007.369176
State	Published - 2007
Event	2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007 - Honolulu, HI, United States Duration: Apr 1 2007 → Apr 5 2007

Publication series

Name	Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007

Conference

Conference	2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007
Country/Territory	United States
City	Honolulu, HI
Period	4/1/07 → 4/5/07

ASJC Scopus subject areas

Artificial Intelligence
Signal Processing
Software
Electrical and Electronic Engineering

Access to Document

10.1109/CIISP.2007.369176

Cite this

Sahba, F., Tizhoosh, H. R., & Salama, M. M. M. A. (2007). Application of opposition-based reinforcement learning in image segmentation. In Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007 (pp. 246-251). Article 4221426 (Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007). https://doi.org/10.1109/CIISP.2007.369176

Application of opposition-based reinforcement learning in image segmentation. / Sahba, Farhang; Tizhoosh, Hamid R.; Salama, Magdy M.M.A.
Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007. 2007. p. 246-251 4221426 (Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Sahba, F, Tizhoosh, HR & Salama, MMMA 2007, Application of opposition-based reinforcement learning in image segmentation. in Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007., 4221426, Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007, pp. 246-251, 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007, Honolulu, HI, United States, 4/1/07. https://doi.org/10.1109/CIISP.2007.369176

Sahba F, Tizhoosh HR, Salama MMMA. Application of opposition-based reinforcement learning in image segmentation. In Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007. 2007. p. 246-251. 4221426. (Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007). doi: 10.1109/CIISP.2007.369176

Sahba, Farhang ; Tizhoosh, Hamid R. ; Salama, Magdy M.M.A. / Application of opposition-based reinforcement learning in image segmentation. Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007. 2007. pp. 246-251 (Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007).

@inproceedings{ad498447918c4fe9a1f76359b922a54a,

title = "Application of opposition-based reinforcement learning in image segmentation",

abstract = "In this paper a method for image segmentation using an opposition-based reinforcement learning scheme is introduced. We use this agent-based approach to optimally find the appropriate local values and segment the object. The agent uses an image and its manually segmented version and takes some actions to change the environment (the quality of segmented image). The agent is provided with a scalar reinforcement signal as reward/punishment. The agent uses this information to explore/exploit the solution space. The values obtained can be used as valuable knowledge to fill the Q-matrix. The results demonstrate potential for applying this new method in the field of medical image segmentation.",

author = "Farhang Sahba and Tizhoosh, {Hamid R.} and Salama, {Magdy M.M.A.}",

year = "2007",

doi = "10.1109/CIISP.2007.369176",

language = "English (US)",

isbn = "1424407079",

series = "Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007",

pages = "246--251",

booktitle = "Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007",

note = "2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007 ; Conference date: 01-04-2007 Through 05-04-2007",

}

TY - GEN

T1 - Application of opposition-based reinforcement learning in image segmentation

AU - Sahba, Farhang

AU - Tizhoosh, Hamid R.

AU - Salama, Magdy M.M.A.

PY - 2007

Y1 - 2007

N2 - In this paper a method for image segmentation using an opposition-based reinforcement learning scheme is introduced. We use this agent-based approach to optimally find the appropriate local values and segment the object. The agent uses an image and its manually segmented version and takes some actions to change the environment (the quality of segmented image). The agent is provided with a scalar reinforcement signal as reward/punishment. The agent uses this information to explore/exploit the solution space. The values obtained can be used as valuable knowledge to fill the Q-matrix. The results demonstrate potential for applying this new method in the field of medical image segmentation.

AB - In this paper a method for image segmentation using an opposition-based reinforcement learning scheme is introduced. We use this agent-based approach to optimally find the appropriate local values and segment the object. The agent uses an image and its manually segmented version and takes some actions to change the environment (the quality of segmented image). The agent is provided with a scalar reinforcement signal as reward/punishment. The agent uses this information to explore/exploit the solution space. The values obtained can be used as valuable knowledge to fill the Q-matrix. The results demonstrate potential for applying this new method in the field of medical image segmentation.

UR - http://www.scopus.com/inward/record.url?scp=34548704982&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548704982&partnerID=8YFLogxK

U2 - 10.1109/CIISP.2007.369176

DO - 10.1109/CIISP.2007.369176

M3 - Conference contribution

AN - SCOPUS:34548704982

SN - 1424407079

SN - 9781424407071

T3 - Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007

SP - 246

EP - 251

BT - Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007

T2 - 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing, CIISP 2007

Y2 - 1 April 2007 through 5 April 2007

ER -

Application of opposition-based reinforcement learning in image segmentation

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this