Using reinforcement learning for image thresholding

Maryam Shokri; Hamid R. Tizhoosh

Using reinforcement learning for image thresholding

Artificial Intelligence and Informatics

Research output: Contribution to journal › Conference article › peer-review

Abstract

A reinforcement-learning agent was introduced to find the optimal threshold for digital images. The agent learnt the optimal threshold for an image through interactions with an experienced user, and by integrating objective domain knowledge. Results showed that the proposed approach could integrate human expert knowledge in an objective or subjective way to overcome the shortcomings of existing methods.

Original language	English (US)
Pages (from-to)	1231-1234
Number of pages	4
Journal	Canadian Conference on Electrical and Computer Engineering
Volume	2
State	Published - 2003
Event	CCECE 2003 Canadian Conference on Electrical and Computer Engineering: Toward a Caring and Humane Technology - Montreal, Canada Duration: May 4 2003 → May 7 2003

Keywords

Image Processing
Image thresholding
Reinforcement learning

ASJC Scopus subject areas

Hardware and Architecture
Electrical and Electronic Engineering

Cite this

@article{3243033e04a0448e88f4a327378f013b,

title = "Using reinforcement learning for image thresholding",

abstract = "A reinforcement-learning agent was introduced to find the optimal threshold for digital images. The agent learnt the optimal threshold for an image through interactions with an experienced user, and by integrating objective domain knowledge. Results showed that the proposed approach could integrate human expert knowledge in an objective or subjective way to overcome the shortcomings of existing methods.",

keywords = "Image Processing, Image thresholding, Reinforcement learning",

author = "Maryam Shokri and Tizhoosh, {Hamid R.}",

year = "2003",

language = "English (US)",

volume = "2",

pages = "1231--1234",

journal = "Canadian Conference on Electrical and Computer Engineering",

issn = "0840-7789",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "CCECE 2003 Canadian Conference on Electrical and Computer Engineering: Toward a Caring and Humane Technology ; Conference date: 04-05-2003 Through 07-05-2003",

}

TY - JOUR

T1 - Using reinforcement learning for image thresholding

AU - Shokri, Maryam

AU - Tizhoosh, Hamid R.

PY - 2003

Y1 - 2003

N2 - A reinforcement-learning agent was introduced to find the optimal threshold for digital images. The agent learnt the optimal threshold for an image through interactions with an experienced user, and by integrating objective domain knowledge. Results showed that the proposed approach could integrate human expert knowledge in an objective or subjective way to overcome the shortcomings of existing methods.

AB - A reinforcement-learning agent was introduced to find the optimal threshold for digital images. The agent learnt the optimal threshold for an image through interactions with an experienced user, and by integrating objective domain knowledge. Results showed that the proposed approach could integrate human expert knowledge in an objective or subjective way to overcome the shortcomings of existing methods.

KW - Image Processing

KW - Image thresholding

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=0141762732&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0141762732&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0141762732

SN - 0840-7789

VL - 2

SP - 1231

EP - 1234

JO - Canadian Conference on Electrical and Computer Engineering

JF - Canadian Conference on Electrical and Computer Engineering

T2 - CCECE 2003 Canadian Conference on Electrical and Computer Engineering: Toward a Caring and Humane Technology

Y2 - 4 May 2003 through 7 May 2003

ER -

Using reinforcement learning for image thresholding

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this