Image Segmentation by Normalized Cut with Shape Information
碩士 === 國立臺灣海洋大學 === 資訊工程學系 === 93 === Image segmentation is a classical problem in compute vision. In the recent years, some researches regard the image segmentation problem as a graph-partitioning problem. Among various graph-partitioning algorithms for image segmentation, of particular interest in...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2005
|
Online Access: | http://ndltd.ncl.edu.tw/handle/89420514405612604883 |
id |
ndltd-TW-093NTOU5392018 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-093NTOU53920182016-06-01T04:25:07Z http://ndltd.ncl.edu.tw/handle/89420514405612604883 Image Segmentation by Normalized Cut with Shape Information 結合形狀資訊之正規化分割影像切割法 Guo-Wei Lin 林國偉 碩士 國立臺灣海洋大學 資訊工程學系 93 Image segmentation is a classical problem in compute vision. In the recent years, some researches regard the image segmentation problem as a graph-partitioning problem. Among various graph-partitioning algorithms for image segmentation, of particular interest in this thesis is the normalized cut because the normalized cut is capable of establishing the relationship between each pair of pixels. However, to our knowledge, all of the graph-partitioning approaches only utilize low-level information about the image. In this thesis, in order to find the contour of the target shape with shape deformations, we propose a new scheme to incorporate high-level information about the target shapes, which is collected by the generalized Hough transform (GHT), into the normalized cut. The experimental results show that our approach can segment out the target shape. In addition, in comparison with the GHT, the proposed approach has better edge continuation, could tolerate larger shape variation, and cover less erroneous contours. Chin-Chun Chang 張欽圳 2005 學位論文 ; thesis 38 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣海洋大學 === 資訊工程學系 === 93 === Image segmentation is a classical problem in compute vision. In the recent years, some researches regard the image segmentation problem as a graph-partitioning problem. Among various graph-partitioning algorithms for image segmentation, of particular interest in this thesis is the normalized cut because the normalized cut is capable of establishing the relationship between each pair of pixels. However, to our knowledge, all of the graph-partitioning approaches only utilize low-level information about the image. In this thesis, in order to find the contour of the target shape with shape deformations, we propose a new scheme to incorporate high-level information about the target shapes, which is collected by the generalized Hough transform (GHT), into the normalized cut. The experimental results show that our approach can segment out the target shape. In addition, in comparison with the GHT, the proposed approach has better edge continuation, could tolerate larger shape variation, and cover less erroneous contours.
|
author2 |
Chin-Chun Chang |
author_facet |
Chin-Chun Chang Guo-Wei Lin 林國偉 |
author |
Guo-Wei Lin 林國偉 |
spellingShingle |
Guo-Wei Lin 林國偉 Image Segmentation by Normalized Cut with Shape Information |
author_sort |
Guo-Wei Lin |
title |
Image Segmentation by Normalized Cut with Shape Information |
title_short |
Image Segmentation by Normalized Cut with Shape Information |
title_full |
Image Segmentation by Normalized Cut with Shape Information |
title_fullStr |
Image Segmentation by Normalized Cut with Shape Information |
title_full_unstemmed |
Image Segmentation by Normalized Cut with Shape Information |
title_sort |
image segmentation by normalized cut with shape information |
publishDate |
2005 |
url |
http://ndltd.ncl.edu.tw/handle/89420514405612604883 |
work_keys_str_mv |
AT guoweilin imagesegmentationbynormalizedcutwithshapeinformation AT línguówěi imagesegmentationbynormalizedcutwithshapeinformation AT guoweilin jiéhéxíngzhuàngzīxùnzhīzhèngguīhuàfēngēyǐngxiàngqiègēfǎ AT línguówěi jiéhéxíngzhuàngzīxùnzhīzhèngguīhuàfēngēyǐngxiàngqiègēfǎ |
_version_ |
1718291216625303552 |