Edge-enhanced segmentation for SAR images
Thesis (M. Eng.), Memorial University of Newfoundland, 1998. Engineering and Applied Science Bibliography: leaves 93-99 Segmentation of Synthetic Aperture Radar (SAR) images is an important step for further image analysis in many applications. However, the segmentation of this kind of image is made...
Main Author: | |
---|---|
Other Authors: | |
Format: | Thesis |
Language: | English |
Published: |
1997
|
Subjects: | |
Online Access: | http://collections.mun.ca/cdm/ref/collection/theses3/id/134355 |
id |
ftmemorialunivdc:oai:collections.mun.ca:theses3/134355 |
---|---|
record_format |
openpolar |
spelling |
ftmemorialunivdc:oai:collections.mun.ca:theses3/134355 2023-05-15T17:23:32+02:00 Edge-enhanced segmentation for SAR images Ju, Chen, 1969- Memorial University of Newfoundland. Faculty of Engineering and Applied Science 1997 100 leaves : ill. Image/jpeg; Application/pdf http://collections.mun.ca/cdm/ref/collection/theses3/id/134355 Eng eng Electronic Theses and Dissertations (10.84 MB) -- http://collections.mun.ca/PDFs/theses/Ju_Chen.pdf a1261241 http://collections.mun.ca/cdm/ref/collection/theses3/id/134355 The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. Paper copy kept in the Centre for Newfoundland Studies, Memorial University Libraries Synthetic aperture radar Image analysis Image processing--Digital techniques Text Electronic thesis or dissertation 1997 ftmemorialunivdc 2015-08-06T19:20:11Z Thesis (M. Eng.), Memorial University of Newfoundland, 1998. Engineering and Applied Science Bibliography: leaves 93-99 Segmentation of Synthetic Aperture Radar (SAR) images is an important step for further image analysis in many applications. However, the segmentation of this kind of image is made difficult by the presence of speckle noise, which is multiplicative rather than additive. Traditional segmentation methods originally designed for either noise-free or White Gaussian noise corrupted images can fail when applied to SAR images. -- Different methods have been previously developed for segmenting SAR images corrupted by speckle. One segmentation method was proposed by Lee and Jurkevich which is quite efficient; it first smooths speckle noise to allow regions to be distinguished in the image histogram, then uses histogram thresholding to segment the filtered image. However, some problems exist with their method: in the filtered image, noise is preserved in edge areas and some fine regions are oversmoothed; while in the segmented image, region boundaries are ragged and some fine features are lost. -- Based on Lee and Jurkevich's initial work, an edge-enhanced segmentation method is proposed in this thesis. The edge-enhanced segmentation method is automated and based on the iterative application of an edge-enhanced speckle smoothing filter. The edge-enhanced filters proposed in this thesis use edge information obtained by a ratio- based edge detector to improve the performance of the filters in noise smoothing as well as in edge and fine feature preservation. Due to the good performance of these edge-enhanced filters, the resulting histogram-thresholded segmented images have accurate and simple region boundaries and well separated regions of both large and small sizes. The proposed method is compared with the previous method proposed by Lee and Jurkevich, in both noise smoothing performance and in segmentation quality. The results are tested on synthetic images as well as airborne SAR images. The tests show that the proposed method produces better image segmentations, particularly in image region boundaries, homogeneous regions and for images with fine features. The proposed edge-enhanced segmentation scheme may be suitable for many SAR image analysis applications such as sea-ice segmentation, forest classification, crop identification, etc. Thesis Newfoundland studies Sea ice University of Newfoundland Memorial University of Newfoundland: Digital Archives Initiative (DAI) |
institution |
Open Polar |
collection |
Memorial University of Newfoundland: Digital Archives Initiative (DAI) |
op_collection_id |
ftmemorialunivdc |
language |
English |
topic |
Synthetic aperture radar Image analysis Image processing--Digital techniques |
spellingShingle |
Synthetic aperture radar Image analysis Image processing--Digital techniques Ju, Chen, 1969- Edge-enhanced segmentation for SAR images |
topic_facet |
Synthetic aperture radar Image analysis Image processing--Digital techniques |
description |
Thesis (M. Eng.), Memorial University of Newfoundland, 1998. Engineering and Applied Science Bibliography: leaves 93-99 Segmentation of Synthetic Aperture Radar (SAR) images is an important step for further image analysis in many applications. However, the segmentation of this kind of image is made difficult by the presence of speckle noise, which is multiplicative rather than additive. Traditional segmentation methods originally designed for either noise-free or White Gaussian noise corrupted images can fail when applied to SAR images. -- Different methods have been previously developed for segmenting SAR images corrupted by speckle. One segmentation method was proposed by Lee and Jurkevich which is quite efficient; it first smooths speckle noise to allow regions to be distinguished in the image histogram, then uses histogram thresholding to segment the filtered image. However, some problems exist with their method: in the filtered image, noise is preserved in edge areas and some fine regions are oversmoothed; while in the segmented image, region boundaries are ragged and some fine features are lost. -- Based on Lee and Jurkevich's initial work, an edge-enhanced segmentation method is proposed in this thesis. The edge-enhanced segmentation method is automated and based on the iterative application of an edge-enhanced speckle smoothing filter. The edge-enhanced filters proposed in this thesis use edge information obtained by a ratio- based edge detector to improve the performance of the filters in noise smoothing as well as in edge and fine feature preservation. Due to the good performance of these edge-enhanced filters, the resulting histogram-thresholded segmented images have accurate and simple region boundaries and well separated regions of both large and small sizes. The proposed method is compared with the previous method proposed by Lee and Jurkevich, in both noise smoothing performance and in segmentation quality. The results are tested on synthetic images as well as airborne SAR images. The tests show that the proposed method produces better image segmentations, particularly in image region boundaries, homogeneous regions and for images with fine features. The proposed edge-enhanced segmentation scheme may be suitable for many SAR image analysis applications such as sea-ice segmentation, forest classification, crop identification, etc. |
author2 |
Memorial University of Newfoundland. Faculty of Engineering and Applied Science |
format |
Thesis |
author |
Ju, Chen, 1969- |
author_facet |
Ju, Chen, 1969- |
author_sort |
Ju, Chen, 1969- |
title |
Edge-enhanced segmentation for SAR images |
title_short |
Edge-enhanced segmentation for SAR images |
title_full |
Edge-enhanced segmentation for SAR images |
title_fullStr |
Edge-enhanced segmentation for SAR images |
title_full_unstemmed |
Edge-enhanced segmentation for SAR images |
title_sort |
edge-enhanced segmentation for sar images |
publishDate |
1997 |
url |
http://collections.mun.ca/cdm/ref/collection/theses3/id/134355 |
genre |
Newfoundland studies Sea ice University of Newfoundland |
genre_facet |
Newfoundland studies Sea ice University of Newfoundland |
op_source |
Paper copy kept in the Centre for Newfoundland Studies, Memorial University Libraries |
op_relation |
Electronic Theses and Dissertations (10.84 MB) -- http://collections.mun.ca/PDFs/theses/Ju_Chen.pdf a1261241 http://collections.mun.ca/cdm/ref/collection/theses3/id/134355 |
op_rights |
The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. |
_version_ |
1766113141021736960 |