The Research of Trend-predicting growing method with Multi Image Feature applied on clipped Gyrus Image Segmentation
碩士 === 國立成功大學 === 電腦與通信工程研究所 === 97 === The segmentation of a medical image is an integrated task. We need to integrate the knowledge of image processing, computer vision and anatomy to complete the task. This thesis describes how to use the techniques of image processing with a blackboard architect...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2009
|
Online Access: | http://ndltd.ncl.edu.tw/handle/81118717551482419927 |
id |
ndltd-TW-097NCKU5652010 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-097NCKU56520102015-11-23T04:03:12Z http://ndltd.ncl.edu.tw/handle/81118717551482419927 The Research of Trend-predicting growing method with Multi Image Feature applied on clipped Gyrus Image Segmentation 以多重影像特徵值為基礎之趨勢預測成長法應用於腦迴切割影像分割之研究 YI-HSIEN CHANG 張逸賢 碩士 國立成功大學 電腦與通信工程研究所 97 The segmentation of a medical image is an integrated task. We need to integrate the knowledge of image processing, computer vision and anatomy to complete the task. This thesis describes how to use the techniques of image processing with a blackboard architecture to generate the contours of the regions of interest. We also integrate another system, 3D Builder, to provide the interface for the users so that we can communicate with our system interactively and view the results of the 3-dimensional reconstruction during the process of recognition. As far as image processing is concerned, we will describe the segmentation methods for the gray matter of gyrus, for helping us find out the correct regions. We hope use the contours to reconstruct 3D objects and find the thickness of the gray matter area, the information that user operate the gyrus 3D object is meaningful when the gray matter’s contour is correct . On the processing of image recognition, we use the globe and local threshold method, and use various characteristic value to help segmentation on the algorithm. eventually, for the Trend predicting on region grow, we collect the local characteristic value information of the confirmed gray matter area, and use the predicting result to help use determine the region grow control. About the blackboard architecture, we add the communication interface between the main system and the knowledge resources in the blackboard system which’s main architecture is already completed. According to professional knowledge, doctors can enter the helpful information into the system in the processes of image recognition. Then we can gain more correct recognition results with knowledge resources. CHEN,LI-HSIANG 陳立祥 2009 學位論文 ; thesis 117 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立成功大學 === 電腦與通信工程研究所 === 97 === The segmentation of a medical image is an integrated task. We need to integrate the knowledge of image processing, computer vision and anatomy to complete the task. This thesis describes how to use the techniques of image
processing with a blackboard architecture to generate the contours of the regions of interest. We also integrate another system, 3D Builder, to provide the interface for the users so that we can communicate with our system interactively and view the results of the 3-dimensional reconstruction during the process of recognition.
As far as image processing is concerned, we will describe the segmentation methods for the gray matter of gyrus, for helping us find out the correct regions. We hope use the contours to reconstruct 3D objects and find the thickness of the gray matter area, the information that user operate the gyrus 3D object is meaningful when the gray matter’s contour is correct . On the processing of image recognition, we use the globe
and local threshold method, and use various characteristic value to help segmentation on the algorithm. eventually, for the Trend predicting on region grow, we collect the local characteristic value information of the confirmed gray matter area, and use the predicting result to help use determine the region grow control.
About the blackboard architecture, we add the communication interface between the main system and the knowledge resources in the blackboard system which’s main architecture is already completed. According to professional knowledge, doctors can enter the helpful information into the system in the processes of image recognition.
Then we can gain more correct recognition results with knowledge resources.
|
author2 |
CHEN,LI-HSIANG |
author_facet |
CHEN,LI-HSIANG YI-HSIEN CHANG 張逸賢 |
author |
YI-HSIEN CHANG 張逸賢 |
spellingShingle |
YI-HSIEN CHANG 張逸賢 The Research of Trend-predicting growing method with Multi Image Feature applied on clipped Gyrus Image Segmentation |
author_sort |
YI-HSIEN CHANG |
title |
The Research of Trend-predicting growing method with Multi Image Feature applied on clipped Gyrus Image Segmentation |
title_short |
The Research of Trend-predicting growing method with Multi Image Feature applied on clipped Gyrus Image Segmentation |
title_full |
The Research of Trend-predicting growing method with Multi Image Feature applied on clipped Gyrus Image Segmentation |
title_fullStr |
The Research of Trend-predicting growing method with Multi Image Feature applied on clipped Gyrus Image Segmentation |
title_full_unstemmed |
The Research of Trend-predicting growing method with Multi Image Feature applied on clipped Gyrus Image Segmentation |
title_sort |
research of trend-predicting growing method with multi image feature applied on clipped gyrus image segmentation |
publishDate |
2009 |
url |
http://ndltd.ncl.edu.tw/handle/81118717551482419927 |
work_keys_str_mv |
AT yihsienchang theresearchoftrendpredictinggrowingmethodwithmultiimagefeatureappliedonclippedgyrusimagesegmentation AT zhāngyìxián theresearchoftrendpredictinggrowingmethodwithmultiimagefeatureappliedonclippedgyrusimagesegmentation AT yihsienchang yǐduōzhòngyǐngxiàngtèzhēngzhíwèijīchǔzhīqūshìyùcèchéngzhǎngfǎyīngyòngyúnǎohuíqiègēyǐngxiàngfēngēzhīyánjiū AT zhāngyìxián yǐduōzhòngyǐngxiàngtèzhēngzhíwèijīchǔzhīqūshìyùcèchéngzhǎngfǎyīngyòngyúnǎohuíqiègēyǐngxiàngfēngēzhīyánjiū AT yihsienchang researchoftrendpredictinggrowingmethodwithmultiimagefeatureappliedonclippedgyrusimagesegmentation AT zhāngyìxián researchoftrendpredictinggrowingmethodwithmultiimagefeatureappliedonclippedgyrusimagesegmentation |
_version_ |
1718134803134414848 |