Segmentation of multispectral MR images through an annealed rough neural network

Yi Ying Chang, Shen-Chuan Tai, Jzau Sheng Lin

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper, multispectral image segmentation using a rough neural network based on an annealed strategy with a cooling schedule is created. The main purpose is to embed an annealed cooling schedule into the rough neural network to construct a segmentation system named annealed rough neural net (ARNN). The classification system is a paradigm for the implementation of annealed reasoning and rough systems in neural network architecture. Instead of all the information in the image are fed into the neural network, the upper- and lower-bound gray level, captured from a training vector in a multispectral image, were fed into a rough neuron in the ARNN. Therefore, only 2-channel images are selected as the training samples if an N-dimensional multispectral image was used. In the simulation results, the proposed network not only reduces the consuming time but also reserves the classification performance.

Original languageEnglish
Pages (from-to)911-919
Number of pages9
JournalNeural Computing and Applications
Volume21
Issue number5
DOIs
Publication statusPublished - 2012 Jul 1

Fingerprint

Neural networks
Cooling
Network architecture
Image segmentation
Neurons

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

@article{3851c36aa939436db7cec0bc9e2c54e7,
title = "Segmentation of multispectral MR images through an annealed rough neural network",
abstract = "In this paper, multispectral image segmentation using a rough neural network based on an annealed strategy with a cooling schedule is created. The main purpose is to embed an annealed cooling schedule into the rough neural network to construct a segmentation system named annealed rough neural net (ARNN). The classification system is a paradigm for the implementation of annealed reasoning and rough systems in neural network architecture. Instead of all the information in the image are fed into the neural network, the upper- and lower-bound gray level, captured from a training vector in a multispectral image, were fed into a rough neuron in the ARNN. Therefore, only 2-channel images are selected as the training samples if an N-dimensional multispectral image was used. In the simulation results, the proposed network not only reduces the consuming time but also reserves the classification performance.",
author = "Chang, {Yi Ying} and Shen-Chuan Tai and Lin, {Jzau Sheng}",
year = "2012",
month = "7",
day = "1",
doi = "10.1007/s00521-011-0724-1",
language = "English",
volume = "21",
pages = "911--919",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",
number = "5",

}

Segmentation of multispectral MR images through an annealed rough neural network. / Chang, Yi Ying; Tai, Shen-Chuan; Lin, Jzau Sheng.

In: Neural Computing and Applications, Vol. 21, No. 5, 01.07.2012, p. 911-919.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Segmentation of multispectral MR images through an annealed rough neural network

AU - Chang, Yi Ying

AU - Tai, Shen-Chuan

AU - Lin, Jzau Sheng

PY - 2012/7/1

Y1 - 2012/7/1

N2 - In this paper, multispectral image segmentation using a rough neural network based on an annealed strategy with a cooling schedule is created. The main purpose is to embed an annealed cooling schedule into the rough neural network to construct a segmentation system named annealed rough neural net (ARNN). The classification system is a paradigm for the implementation of annealed reasoning and rough systems in neural network architecture. Instead of all the information in the image are fed into the neural network, the upper- and lower-bound gray level, captured from a training vector in a multispectral image, were fed into a rough neuron in the ARNN. Therefore, only 2-channel images are selected as the training samples if an N-dimensional multispectral image was used. In the simulation results, the proposed network not only reduces the consuming time but also reserves the classification performance.

AB - In this paper, multispectral image segmentation using a rough neural network based on an annealed strategy with a cooling schedule is created. The main purpose is to embed an annealed cooling schedule into the rough neural network to construct a segmentation system named annealed rough neural net (ARNN). The classification system is a paradigm for the implementation of annealed reasoning and rough systems in neural network architecture. Instead of all the information in the image are fed into the neural network, the upper- and lower-bound gray level, captured from a training vector in a multispectral image, were fed into a rough neuron in the ARNN. Therefore, only 2-channel images are selected as the training samples if an N-dimensional multispectral image was used. In the simulation results, the proposed network not only reduces the consuming time but also reserves the classification performance.

UR - http://www.scopus.com/inward/record.url?scp=84865616390&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84865616390&partnerID=8YFLogxK

U2 - 10.1007/s00521-011-0724-1

DO - 10.1007/s00521-011-0724-1

M3 - Article

VL - 21

SP - 911

EP - 919

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 5

ER -