Image segmentation using neighborhood inspiring pulse coupled neural network

Dansong Cheng; Xiaofang Liu; Xianglong Tang; Jiafeng Liu

Image segmentation using neighborhood inspiring pulse coupled neural network

Dansong Cheng^*
, Xiaofang Liu
, Xianglong Tang
, Jiafeng Liu

^*Corresponding author for this work

Faculty of Computing

School of Electrical Engineering and Automation, Harbin Institute of Technology
Harbin Institute of Technology

Research output: Contribution to journal › Article › peer-review

3 Scopus citations

Abstract

An approach to image segmentation was introduced by using neighborhood inspiring pulse coupled neural network (NIPCNN). The neighborhoods considering brightness and distribution of the pixels were modeled into a factor to control the linking and the internal activity. Criteria based on majority rule controls the process, and threshold adjustment for heiborhoods within on iterative ensures the integrated result. Experiments of several types of images were implemented with the proposed method and the experimental results were compared with classical methods to demonstrate its validity.

Original language	English
Pages (from-to)	33-37
Number of pages	5
Journal	Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition)
Volume	37
Issue number	5
State	Published - May 2009

Keywords

Image segmentation
Majority rule
Neighborhood inspiring
Pulse coupled neural network (PCNN)
Square neighborhood

Cite this

@article{ed36b54f75d4455d8da8dcd86c55c40f,

title = "Image segmentation using neighborhood inspiring pulse coupled neural network",

abstract = "An approach to image segmentation was introduced by using neighborhood inspiring pulse coupled neural network (NIPCNN). The neighborhoods considering brightness and distribution of the pixels were modeled into a factor to control the linking and the internal activity. Criteria based on majority rule controls the process, and threshold adjustment for heiborhoods within on iterative ensures the integrated result. Experiments of several types of images were implemented with the proposed method and the experimental results were compared with classical methods to demonstrate its validity.",

keywords = "Image segmentation, Majority rule, Neighborhood inspiring, Pulse coupled neural network (PCNN), Square neighborhood",

author = "Dansong Cheng and Xiaofang Liu and Xianglong Tang and Jiafeng Liu",

year = "2009",

month = may,

language = "英语",

volume = "37",

pages = "33--37",

journal = "Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition)",

issn = "1671-4512",

publisher = "Huazhong University of Science and Technology",

number = "5",

}

TY - JOUR

T1 - Image segmentation using neighborhood inspiring pulse coupled neural network

AU - Cheng, Dansong

AU - Liu, Xiaofang

AU - Tang, Xianglong

AU - Liu, Jiafeng

PY - 2009/5

Y1 - 2009/5

N2 - An approach to image segmentation was introduced by using neighborhood inspiring pulse coupled neural network (NIPCNN). The neighborhoods considering brightness and distribution of the pixels were modeled into a factor to control the linking and the internal activity. Criteria based on majority rule controls the process, and threshold adjustment for heiborhoods within on iterative ensures the integrated result. Experiments of several types of images were implemented with the proposed method and the experimental results were compared with classical methods to demonstrate its validity.

AB - An approach to image segmentation was introduced by using neighborhood inspiring pulse coupled neural network (NIPCNN). The neighborhoods considering brightness and distribution of the pixels were modeled into a factor to control the linking and the internal activity. Criteria based on majority rule controls the process, and threshold adjustment for heiborhoods within on iterative ensures the integrated result. Experiments of several types of images were implemented with the proposed method and the experimental results were compared with classical methods to demonstrate its validity.

KW - Image segmentation

KW - Majority rule

KW - Neighborhood inspiring

KW - Pulse coupled neural network (PCNN)

KW - Square neighborhood

UR - https://www.scopus.com/pages/publications/67649148275

M3 - 文章

AN - SCOPUS:67649148275

SN - 1671-4512

VL - 37

SP - 33

EP - 37

JO - Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition)

JF - Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition)

IS - 5

ER -

Image segmentation using neighborhood inspiring pulse coupled neural network

Abstract

Keywords

Other files and links

Fingerprint

Cite this