An Adaptive Threshold for the Canny Algorithm With Deep Reinforcement Learning

The Canny algorithm is widely used for edge detection. It requires the adjustment of parameters to obtain a high-quality edge image. Several methods can select them automatically, but they cannot cover the diverse variations on an image. In the Canny algorithm, we need to set values of three paramet...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Keong-Hun Choi, Jong-Eun Ha
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Edge detection deep Q-network deep reinforcement learning Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/9523fb1722094894875e95f4a04e927e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9523fb1722094894875e95f4a04e927e
record_format	dspace
spelling	oai:doaj.org-article:9523fb1722094894875e95f4a04e927e2021-12-02T00:00:36ZAn Adaptive Threshold for the Canny Algorithm With Deep Reinforcement Learning2169-353610.1109/ACCESS.2021.3130132https://doaj.org/article/9523fb1722094894875e95f4a04e927e2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9624973/https://doaj.org/toc/2169-3536The Canny algorithm is widely used for edge detection. It requires the adjustment of parameters to obtain a high-quality edge image. Several methods can select them automatically, but they cannot cover the diverse variations on an image. In the Canny algorithm, we need to set values of three parameters. One is related to smoothing window size, and the other two are the low and high threshold. In this paper, we assume that the smoothing window size is fixed to a predefined size. This paper proposes a method to provide adaptive thresholds for the Canny algorithm, which operates well on images acquired under various variations. We select optimal values of two thresholds adaptively using an algorithm based on the Deep Q-Network (DQN). We introduce a state model, a policy model, and a reward model to formulate the given problem in deep reinforcement learning. The proposed method has the advantage that it can adapt to a new environment using only images without labels, unlike the existing supervised way. We show the feasibility of the proposed algorithm by diverse experimental results.Keong-Hun ChoiJong-Eun HaIEEEarticleEdge detectiondeep Q-networkdeep reinforcement learningElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 156846-156856 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Edge detection deep Q-network deep reinforcement learning Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Edge detection deep Q-network deep reinforcement learning Electrical engineering. Electronics. Nuclear engineering TK1-9971 Keong-Hun Choi Jong-Eun Ha An Adaptive Threshold for the Canny Algorithm With Deep Reinforcement Learning
description	The Canny algorithm is widely used for edge detection. It requires the adjustment of parameters to obtain a high-quality edge image. Several methods can select them automatically, but they cannot cover the diverse variations on an image. In the Canny algorithm, we need to set values of three parameters. One is related to smoothing window size, and the other two are the low and high threshold. In this paper, we assume that the smoothing window size is fixed to a predefined size. This paper proposes a method to provide adaptive thresholds for the Canny algorithm, which operates well on images acquired under various variations. We select optimal values of two thresholds adaptively using an algorithm based on the Deep Q-Network (DQN). We introduce a state model, a policy model, and a reward model to formulate the given problem in deep reinforcement learning. The proposed method has the advantage that it can adapt to a new environment using only images without labels, unlike the existing supervised way. We show the feasibility of the proposed algorithm by diverse experimental results.
format	article
author	Keong-Hun Choi Jong-Eun Ha
author_facet	Keong-Hun Choi Jong-Eun Ha
author_sort	Keong-Hun Choi
title	An Adaptive Threshold for the Canny Algorithm With Deep Reinforcement Learning
title_short	An Adaptive Threshold for the Canny Algorithm With Deep Reinforcement Learning
title_full	An Adaptive Threshold for the Canny Algorithm With Deep Reinforcement Learning
title_fullStr	An Adaptive Threshold for the Canny Algorithm With Deep Reinforcement Learning
title_full_unstemmed	An Adaptive Threshold for the Canny Algorithm With Deep Reinforcement Learning
title_sort	adaptive threshold for the canny algorithm with deep reinforcement learning
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/9523fb1722094894875e95f4a04e927e
work_keys_str_mv	AT keonghunchoi anadaptivethresholdforthecannyalgorithmwithdeepreinforcementlearning AT jongeunha anadaptivethresholdforthecannyalgorithmwithdeepreinforcementlearning AT keonghunchoi adaptivethresholdforthecannyalgorithmwithdeepreinforcementlearning AT jongeunha adaptivethresholdforthecannyalgorithmwithdeepreinforcementlearning
_version_	1718404000517193728

An Adaptive Threshold for the Canny Algorithm With Deep Reinforcement Learning

Ejemplares similares