A new image segmentation method based on modified intersecting cortical model

Jian Wei Niu; Si Si Shen; Chao Tong; Xiao Peng Gao; Kong Qiao Wang

A new image segmentation method based on modified intersecting cortical model

Jian Wei Niu^*
, Si Si Shen
, Chao Tong
, Xiao Peng Gao
, Kong Qiao Wang

^*Corresponding author for this work

School of Computer Science and Engineering

Beihang University
Nokia China Research Center

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

3 Scopus citations

Abstract

An image segmentation method based on the modified intersecting cortical model (MICM) is proposed to set the MICM parameters adaptively according to the different characteristics of images and choose the optimal segmentation results automatically, which are two main obstacles for the basic intersecting cortical model (ICM) to be used in practice. Experiments show that the comprehensive evaluation value of MICM is close to those of basic pulse coupled neural network (PCNN) and basic intersecting cortical model. Compared with the fuzzy C-means algorithm and OTSU algorithm, MICM is of visually better segmentation and the comprehensive evaluation value of MICM increases by approximately 15% and 13% respectively.

Original language	English
Pages (from-to)	56-60
Number of pages	5
Journal	Beijing Youdian Xueyuan Xuebao/Journal of Beijing University of Posts And Telecommunications
Volume	33
Issue number	1
State	Published - Feb 2010

Keywords

Image segmentation
Intersecting cortical model
Mutual information
Self-adaptive

Cite this

@article{830e4f5f1f4b4401917572081eeb468a,

title = "A new image segmentation method based on modified intersecting cortical model",

abstract = "An image segmentation method based on the modified intersecting cortical model (MICM) is proposed to set the MICM parameters adaptively according to the different characteristics of images and choose the optimal segmentation results automatically, which are two main obstacles for the basic intersecting cortical model (ICM) to be used in practice. Experiments show that the comprehensive evaluation value of MICM is close to those of basic pulse coupled neural network (PCNN) and basic intersecting cortical model. Compared with the fuzzy C-means algorithm and OTSU algorithm, MICM is of visually better segmentation and the comprehensive evaluation value of MICM increases by approximately 15\% and 13\% respectively.",

keywords = "Image segmentation, Intersecting cortical model, Mutual information, Self-adaptive",

author = "Niu, \{Jian Wei\} and Shen, \{Si Si\} and Chao Tong and Gao, \{Xiao Peng\} and Wang, \{Kong Qiao\}",

year = "2010",

month = feb,

language = "英语",

volume = "33",

pages = "56--60",

journal = "Beijing Youdian Xueyuan Xuebao/Journal of Beijing University of Posts And Telecommunications",

issn = "1007-5321",

publisher = "Beijing University of Posts and Telecommunications",

number = "1",

}

TY - JOUR

T1 - A new image segmentation method based on modified intersecting cortical model

AU - Niu, Jian Wei

AU - Shen, Si Si

AU - Tong, Chao

AU - Gao, Xiao Peng

AU - Wang, Kong Qiao

PY - 2010/2

Y1 - 2010/2

N2 - An image segmentation method based on the modified intersecting cortical model (MICM) is proposed to set the MICM parameters adaptively according to the different characteristics of images and choose the optimal segmentation results automatically, which are two main obstacles for the basic intersecting cortical model (ICM) to be used in practice. Experiments show that the comprehensive evaluation value of MICM is close to those of basic pulse coupled neural network (PCNN) and basic intersecting cortical model. Compared with the fuzzy C-means algorithm and OTSU algorithm, MICM is of visually better segmentation and the comprehensive evaluation value of MICM increases by approximately 15% and 13% respectively.

AB - An image segmentation method based on the modified intersecting cortical model (MICM) is proposed to set the MICM parameters adaptively according to the different characteristics of images and choose the optimal segmentation results automatically, which are two main obstacles for the basic intersecting cortical model (ICM) to be used in practice. Experiments show that the comprehensive evaluation value of MICM is close to those of basic pulse coupled neural network (PCNN) and basic intersecting cortical model. Compared with the fuzzy C-means algorithm and OTSU algorithm, MICM is of visually better segmentation and the comprehensive evaluation value of MICM increases by approximately 15% and 13% respectively.

KW - Image segmentation

KW - Intersecting cortical model

KW - Mutual information

KW - Self-adaptive

UR - https://www.scopus.com/pages/publications/77951907950

M3 - 文章

AN - SCOPUS:77951907950

SN - 1007-5321

VL - 33

SP - 56

EP - 60

JO - Beijing Youdian Xueyuan Xuebao/Journal of Beijing University of Posts And Telecommunications

JF - Beijing Youdian Xueyuan Xuebao/Journal of Beijing University of Posts And Telecommunications

IS - 1

ER -

A new image segmentation method based on modified intersecting cortical model

Abstract

Keywords

Other files and links

Fingerprint

Cite this