The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dans cet article, une méthode de segmentation d’images couleur à seuillage multiniveau est proposée à l’aide d’un algorithme modifié de colonie d’abeilles artificielles (ABC). Dans ce travail, afin d'améliorer la capacité de recherche locale de l'algorithme ABC, l'algorithme Krill Herd est incorporé dans sa phase d'abeilles observateurs. L'algorithme proposé est nommé algorithme de colonie d'abeilles artificielles modifié par le troupeau de Krill (algorithme KABC). Les résultats de l'expérience vérifient la robustesse de l'algorithme KABC, ainsi que son amélioration en termes d'optimisation de la précision et de la vitesse de convergence. Dans ce travail, l'algorithme KABC est utilisé pour résoudre le problème du seuillage multiniveau pour la segmentation des images couleur. Pour gérer la variation de luminance, plutôt que d'utiliser un histogramme en échelle de gris, une méthode de prétraitement spatiale HSV est proposée pour obtenir un vecteur de caractéristiques 1D. L'algorithme KABC est ensuite appliqué pour trouver les seuils du vecteur de caractéristiques. Enfin, une recherche locale supplémentaire autour des solutions quasi optimales est utilisée pour améliorer la précision de la segmentation. Dans cette étape, nous utilisons une fonction objectif modifiée qui combine la matrice d'indice de similarité structurelle (SSIM) avec l'entropie de Kapur. La méthode de prétraitement, l'optimisation globale avec l'algorithme KABC et l'étape d'optimisation locale forment l'ensemble de la méthode de segmentation d'images couleur. Les résultats de l'expérience montrent une amélioration de la précision de la segmentation avec la méthode proposée.
Sipeng ZHANG
Zhejiang University
Wei JIANG
Zhejiang University
Shin'ichi SATOH
National Institute of Informatics
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Sipeng ZHANG, Wei JIANG, Shin'ichi SATOH, "Multilevel Thresholding Color Image Segmentation Using a Modified Artificial Bee Colony Algorithm" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 8, pp. 2064-2071, August 2018, doi: 10.1587/transinf.2017EDP7183.
Abstract: In this paper, a multilevel thresholding color image segmentation method is proposed using a modified Artificial Bee Colony(ABC) algorithm. In this work, in order to improve the local search ability of ABC algorithm, Krill Herd algorithm is incorporated into its onlooker bees phase. The proposed algorithm is named as Krill herd-inspired modified Artificial Bee Colony algorithm (KABC algorithm). Experiment results verify the robustness of KABC algorithm, as well as its improvement in optimizing accuracy and convergence speed. In this work, KABC algorithm is used to solve the problem of multilevel thresholding for color image segmentation. To deal with luminance variation, rather than using gray scale histogram, a HSV space-based pre-processing method is proposed to obtain 1D feature vector. KABC algorithm is then applied to find thresholds of the feature vector. At last, an additional local search around the quasi-optimal solutions is employed to improve segmentation accuracy. In this stage, we use a modified objective function which combines Structural Similarity Index Matrix (SSIM) with Kapur's entropy. The pre-processing method, the global optimization with KABC algorithm and the local optimization stage form the whole color image segmentation method. Experiment results show enhance in accuracy of segmentation with the proposed method.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDP7183/_p
Copier
@ARTICLE{e101-d_8_2064,
author={Sipeng ZHANG, Wei JIANG, Shin'ichi SATOH, },
journal={IEICE TRANSACTIONS on Information},
title={Multilevel Thresholding Color Image Segmentation Using a Modified Artificial Bee Colony Algorithm},
year={2018},
volume={E101-D},
number={8},
pages={2064-2071},
abstract={In this paper, a multilevel thresholding color image segmentation method is proposed using a modified Artificial Bee Colony(ABC) algorithm. In this work, in order to improve the local search ability of ABC algorithm, Krill Herd algorithm is incorporated into its onlooker bees phase. The proposed algorithm is named as Krill herd-inspired modified Artificial Bee Colony algorithm (KABC algorithm). Experiment results verify the robustness of KABC algorithm, as well as its improvement in optimizing accuracy and convergence speed. In this work, KABC algorithm is used to solve the problem of multilevel thresholding for color image segmentation. To deal with luminance variation, rather than using gray scale histogram, a HSV space-based pre-processing method is proposed to obtain 1D feature vector. KABC algorithm is then applied to find thresholds of the feature vector. At last, an additional local search around the quasi-optimal solutions is employed to improve segmentation accuracy. In this stage, we use a modified objective function which combines Structural Similarity Index Matrix (SSIM) with Kapur's entropy. The pre-processing method, the global optimization with KABC algorithm and the local optimization stage form the whole color image segmentation method. Experiment results show enhance in accuracy of segmentation with the proposed method.},
keywords={},
doi={10.1587/transinf.2017EDP7183},
ISSN={1745-1361},
month={August},}
Copier
TY - JOUR
TI - Multilevel Thresholding Color Image Segmentation Using a Modified Artificial Bee Colony Algorithm
T2 - IEICE TRANSACTIONS on Information
SP - 2064
EP - 2071
AU - Sipeng ZHANG
AU - Wei JIANG
AU - Shin'ichi SATOH
PY - 2018
DO - 10.1587/transinf.2017EDP7183
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2018
AB - In this paper, a multilevel thresholding color image segmentation method is proposed using a modified Artificial Bee Colony(ABC) algorithm. In this work, in order to improve the local search ability of ABC algorithm, Krill Herd algorithm is incorporated into its onlooker bees phase. The proposed algorithm is named as Krill herd-inspired modified Artificial Bee Colony algorithm (KABC algorithm). Experiment results verify the robustness of KABC algorithm, as well as its improvement in optimizing accuracy and convergence speed. In this work, KABC algorithm is used to solve the problem of multilevel thresholding for color image segmentation. To deal with luminance variation, rather than using gray scale histogram, a HSV space-based pre-processing method is proposed to obtain 1D feature vector. KABC algorithm is then applied to find thresholds of the feature vector. At last, an additional local search around the quasi-optimal solutions is employed to improve segmentation accuracy. In this stage, we use a modified objective function which combines Structural Similarity Index Matrix (SSIM) with Kapur's entropy. The pre-processing method, the global optimization with KABC algorithm and the local optimization stage form the whole color image segmentation method. Experiment results show enhance in accuracy of segmentation with the proposed method.
ER -