Development Platform of Active Contour Models
碩士 === 國立清華大學 === 生醫工程與環境科學系 === 105 === In image processing, image segmentation is used in application likes object detection, face recognition, machine vision, medical image. Active contour model, an important base tool for image segmentation, is an energy-minimizing spline. After reaching force b...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2016
|
Online Access: | http://ndltd.ncl.edu.tw/handle/wv4d4c |
id |
ndltd-TW-105NTHU5810003 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-105NTHU58100032019-05-15T23:09:08Z http://ndltd.ncl.edu.tw/handle/wv4d4c Development Platform of Active Contour Models 主動輪廓開發平台 Lin,Ching 林靜 碩士 國立清華大學 生醫工程與環境科學系 105 In image processing, image segmentation is used in application likes object detection, face recognition, machine vision, medical image. Active contour model, an important base tool for image segmentation, is an energy-minimizing spline. After reaching force balance, active contour model extracts object outline. However, active contour model has several drawbacks. It fails to detect concave boundaries and is not attracted to distant edges. For application to all kinds of images, we need to improve active contour model. Several methods has also been proposed for active contour model, but they only partially resolved the problems. In this study, we define an another energy term called pressure energy and add this energy term to the system of energy minimization. The force derived from that energy term lets active contour model find the desired solution. The interaction between pressure and internal force makes active contour model move stably. Compared with other methods indicates pressure model improve the performance of active contour model. Experiments show that our method can extract object boundaries efficiently and stably. Hsu,Ching Han 許靖涵 2016 學位論文 ; thesis 65 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立清華大學 === 生醫工程與環境科學系 === 105 === In image processing, image segmentation is used in application likes object detection, face recognition, machine vision, medical image. Active contour model, an
important base tool for image segmentation, is an energy-minimizing spline. After reaching force balance, active contour model extracts object outline. However, active
contour model has several drawbacks. It fails to detect concave boundaries and is not attracted to distant edges. For application to all kinds of images, we need to improve active contour model.
Several methods has also been proposed for active contour model, but they only partially resolved the problems. In this study, we define an another energy term called pressure energy and add this energy term to the system of energy minimization. The force derived from that energy term lets active contour model find the desired solution.
The interaction between pressure and internal force makes active contour model move stably. Compared with other methods indicates pressure model improve the performance of active contour model. Experiments show that our method can extract object boundaries efficiently and stably.
|
author2 |
Hsu,Ching Han |
author_facet |
Hsu,Ching Han Lin,Ching 林靜 |
author |
Lin,Ching 林靜 |
spellingShingle |
Lin,Ching 林靜 Development Platform of Active Contour Models |
author_sort |
Lin,Ching |
title |
Development Platform of Active Contour Models |
title_short |
Development Platform of Active Contour Models |
title_full |
Development Platform of Active Contour Models |
title_fullStr |
Development Platform of Active Contour Models |
title_full_unstemmed |
Development Platform of Active Contour Models |
title_sort |
development platform of active contour models |
publishDate |
2016 |
url |
http://ndltd.ncl.edu.tw/handle/wv4d4c |
work_keys_str_mv |
AT linching developmentplatformofactivecontourmodels AT línjìng developmentplatformofactivecontourmodels AT linching zhǔdònglúnkuòkāifāpíngtái AT línjìng zhǔdònglúnkuòkāifāpíngtái |
_version_ |
1719141842823413760 |