SOM based segmentation method for water region detection in satellite images

Research output: Contribution to journalArticle

Abstract

There is increasing desire and need in research of water region detection owing to the unexpected natural disaster that lead to financial, environment and human losses. Surveying of water region and research on its feature is very basic step for many planning, especially for countries like Japan, where tsunami has caused the changes on water region in March, 2011. Essentially, identifying water region from satellite images is one of the grand steps of water resources management for a country. Professional and academic institutions play a vital role in the management of water resources as they are instrumental in research. The objective of this paper is to identify the water region from satellite image. In this paper, the segmentation algorithm based on SOM (self-organizing map) neural network with compression pre-processing by wavelet transform and image smoothing using Gaussian low-pass frequency domain filters are presented.
Original languageEnglish
Pages (from-to)95-100
Number of pages6
JournalWorld Journal of Engineering
Volume10
Issue number1
DOIs
Publication statusPublished - 2011

Fingerprint

Self organizing maps
segmentation
Satellites
Water
Water resources
water
Tsunamis
Surveying
natural disaster
smoothing
tsunami
Disasters
Wavelet transforms
surveying
wavelet
transform
water resource
compression
satellite image
detection

Cite this

@article{6fb78a8560c44140b60ed7809301111b,
title = "SOM based segmentation method for water region detection in satellite images",
abstract = "There is increasing desire and need in research of water region detection owing to the unexpected natural disaster that lead to financial, environment and human losses. Surveying of water region and research on its feature is very basic step for many planning, especially for countries like Japan, where tsunami has caused the changes on water region in March, 2011. Essentially, identifying water region from satellite images is one of the grand steps of water resources management for a country. Professional and academic institutions play a vital role in the management of water resources as they are instrumental in research. The objective of this paper is to identify the water region from satellite image. In this paper, the segmentation algorithm based on SOM (self-organizing map) neural network with compression pre-processing by wavelet transform and image smoothing using Gaussian low-pass frequency domain filters are presented.",
author = "{V. Janahiraman}, Tiagrajah and Kong Win",
year = "2011",
doi = "10.1260/1708-5284.10.1.95",
language = "English",
volume = "10",
pages = "95--100",
journal = "World Journal of Engineering",
issn = "1708-5284",
publisher = "Multi-Science Publishing Co. Ltd",
number = "1",

}

SOM based segmentation method for water region detection in satellite images. / V. Janahiraman, Tiagrajah; Win, Kong.

In: World Journal of Engineering, Vol. 10, No. 1, 2011, p. 95-100.

Research output: Contribution to journalArticle

TY - JOUR

T1 - SOM based segmentation method for water region detection in satellite images

AU - V. Janahiraman, Tiagrajah

AU - Win, Kong

PY - 2011

Y1 - 2011

N2 - There is increasing desire and need in research of water region detection owing to the unexpected natural disaster that lead to financial, environment and human losses. Surveying of water region and research on its feature is very basic step for many planning, especially for countries like Japan, where tsunami has caused the changes on water region in March, 2011. Essentially, identifying water region from satellite images is one of the grand steps of water resources management for a country. Professional and academic institutions play a vital role in the management of water resources as they are instrumental in research. The objective of this paper is to identify the water region from satellite image. In this paper, the segmentation algorithm based on SOM (self-organizing map) neural network with compression pre-processing by wavelet transform and image smoothing using Gaussian low-pass frequency domain filters are presented.

AB - There is increasing desire and need in research of water region detection owing to the unexpected natural disaster that lead to financial, environment and human losses. Surveying of water region and research on its feature is very basic step for many planning, especially for countries like Japan, where tsunami has caused the changes on water region in March, 2011. Essentially, identifying water region from satellite images is one of the grand steps of water resources management for a country. Professional and academic institutions play a vital role in the management of water resources as they are instrumental in research. The objective of this paper is to identify the water region from satellite image. In this paper, the segmentation algorithm based on SOM (self-organizing map) neural network with compression pre-processing by wavelet transform and image smoothing using Gaussian low-pass frequency domain filters are presented.

U2 - 10.1260/1708-5284.10.1.95

DO - 10.1260/1708-5284.10.1.95

M3 - Article

VL - 10

SP - 95

EP - 100

JO - World Journal of Engineering

JF - World Journal of Engineering

SN - 1708-5284

IS - 1

ER -