(3.215.183.251) 您好!臺灣時間:2021/04/22 21:28
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:李嘉紘
研究生(外文):Lee ,Jia-Hong
論文名稱:以幾何特徵頻譜於紋理分析之研究
論文名稱(外文):A study of texture analysis using geometrical feature spectra
指導教授:薛元澤薛元澤引用關係
指導教授(外文):Yuang-Cheh Hsueh
學位類別:博士
校院名稱:國立交通大學
系所名稱:資訊科學學系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:1996
畢業學年度:84
語文別:英文
論文頁數:103
中文關鍵詞:紋理分析遺傳演算法紋理特徵形態運算
外文關鍵詞:Texture AnalysisGenetic AlgorithmsTexture gical Operations
相關次數:
  • 被引用被引用:0
  • 點閱點閱:177
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
對於許多不同形式的影像分析,紋理是一項重要的特性,紋理分析在檢視
物體的表面上扮演很重要的角色,而且已經被廣泛地應用在各種不同領域
的影像分析;包含醫學影像、遙測影像、顯微影像等。紋理分析的方法主
要可分為兩大類:結構方法及統計方法,結構方法著重紋理基本元素及取
代法則的製定;統計的方法主要的問題在於紋理特徵的抽取,大部分抽取
特徵的方法是從紋理影像中量測某種特徵的統計值(如能量的平均值標準
差等)或是直接以特徵的統計分佈來做紋理的分析及分類。本文主要是提
出新的紋理特徵配合特徵的統計分佈來作紋理分析及分類,內容可分三部
分,第一部分是Triangle Mesh Model的方法,我們將紋理影像視為三維
度的三角形所組成,然後利用這些三角形的法向量、面積的分佈來分析紋
理,三角形的法向量分佈可以用來分析紋理的方向;而三角形的面積分佈
可以用來分析紋理的顆粒大小。第二部分是以形態運算來定義紋理的區域
特徵,Morphological Gradient 和 Modified Hit-or-Miss運算被使用來
作紋理的區域特徵,紋理的Morphological Gradient分佈可以用來分析此
紋理的粗糙程度;而Modified Hit-or-Miss運算在作紋理分析的觀念是先
定義一組較小的特殊圖案(結構元素),利用這些特殊圖案與待分類紋理之
間match的程度高低來作紋理分類。但是在作形態運算時,結構元素的形
狀及內容會影響到運算的結果,所以結構元素的形狀及內容的選定是一個
問題。在第三部分,我們利用遺傳演算法(Genetic Algorithms)來學習並
決定較佳的結構元素以提高紋理分類的辨識率。上述方法在作紋理分類時
皆直接以特徵的統計分佈來做紋理的分析及分類,並以特徵的統計分佈之
距離來量測紋理之間的差距。最後,我們嘗試作碳鋼顯微影像的分析。碳
鋼所建構的材料早以被人類所廣汎使用,從事碳鋼顯微影像之金相研究不
只對鋼材特性有所了解,亦有助於對其它金屬合金固態反應的認知,但目
前利用碳鋼顯微影像的分析來判斷其所含碳含量時,須利用標準顯微影像
圖鑑來比對,既不客觀又費時間。因此有其自動化的需求。我們試著利用
所提出的統計分佈來作不同含碳量碳鋼顯微影像的分類,實驗結果得到相
當高的辨識率,說明了此方法在建立碳鋼顯微影像自動化辨識系統的可行
性。
Texture is an important characteristic for the analysis of many
different types of images. Texture analysis plays a critical
role in inspecting surfaces and provides important techniques
in a variety of applications ranging from medical imaging to
remote sensing. Texture analysis can be divided into two
components: structural and statistical approaches. Structural
approaches try to describe a repetitive texture in terms of the
primitive elements and placement rules that describe
geometrical relationships between these elements. In
statistical approach, the major problem is the extraction of
texture features. Most of the approaches to texture analysis
quantify the texture measures by single values (means,
variances etc.) or directly use the feature distribution. The
thesis proposes new texture features and uses the corresponding
feature distribution for texture analysis and classification.
Three parts are included in the thesis. The first one is the
Triangle Mesh Model approach. The main concept of this approach
is that texture images can be considered as a set of three
dimensional triangles. The normals and area distribution of
these triangles are used as texture features. In the second
part, we use morphological operations to extract geometrical
texture features. Morphological gradient and modified hit-or-
miss operations are applied in our experiments. In order to
demonstrate the discrimination performance of the proposed
texture features, natural textures from Brodatz album are used
for classification. Experimental results show that our methods
have good performances in texture classification. Since the
content of the structuring elements will effect the features
computed by morphological operations, in part three, genetic
algorithms are used to dynamically select near optimal
structuring elements to achieve high classification rates. In
addition, we also focus on the analysis for carbon steel
micrographs. The current practice of carbon steel sample
analysis with
COVER
ABSTRACT(IN CHINESE)
ABSTRACT
ACKNOWLEDGMENTS
CONTENTS
LIST OF TABLES
LIST OF FIGURES
1 INTRODUCTION
1.1 Research Motivation
1.2 Relative Surveys for Texture Analysis
1.2.1 Fractal Dimension and Peano Scan Curve Method
1.2.2 Morphological Gradient Method for Texture Surface Area
1.2.3 Peleg et. al Method
1.2.4 The Spatial Gray-Level Dependence Matrix Method
1.2.5 The Gray-Level Difference Statistic Method
1.2.6 Texture Spectrum Method
1.3 Overview the Proposed Methods
1.3.1 Texture Sufrace Description Using Multiple Space Filling Curves and Triangle Mesh Model
1.3.2 Modified Texture Spectrum Methods
1.3.3 Genetic Alorithms Based Texture Classification
1.4 Organization of Thesis
2 TEXTURE SURFACE DESCRIPTION USING MULTIPLE SPACE FILLING CURVES METHOD AND TRIANGLE-MESH MODEL
2.1 Introduction
2.2 Multile Space Filling Curves Method
2.2.1 Multiple Space Filling Curves
2.2.2 Texture Feature Extraction
2.2.3 Texutre Classification and Results
2.3 Triangle-Mesh Model
2.3.1 Triangle-Mesh Model
2.3.2 TMM-Based Texture Feature Extraction
A.Surface Normal and Texture Normal Spectrum
B.Surface Area and Texture Area Spectrum
2.3.3 Texture Classification and Results
3 MODIFIED TEXTURE SPECTRUM METHODS
3.1 Introduction
3.2 Directional Texture Specturem Method
3.3 Morphological Gradient Texture Specturm Method
3.3.1 Morphological Gradient Texture Specturm
3.3.2 Rotation Invariant Property of MGTS
3.3.3 Texture Directionality Extracted From Morphological Gradients
3.4 Modified Hit-or-Miss Texture Spectrum Method
3.4.1 Introduction
3.4.2 Modified Hit-or-Miss Transform
3.4.3 Modified Hit-or-Miss Texture Spectrum
3.5 Texture Classification and Results
3.6 Classification of Other Textures
3.6.1 Carbon Steel Micrographs
3.6.2 Texitle Textures
4 HENETIC-BASED TEXTURE CLASSIFICATION
4.1 Introduction
4.2 Major Structure of Genetic Algorithm
4.2.1 The major structure of a basic genetic algorithm
4.2.2 The basic operations of a basic geetic algorithm
4.3 Genetic-Based Texture Classification Model Using Morphological Featurs
4.3.1 Review of Morphological Gradient Method
4.3.2 Morphological Gradient Texture Spectrum
4.3.3 Modified Hit-or-Miss Texture Spectrum
5 CONCLUSIONS AND FUTURE WORK
5.1 Conclusions
5.2 Suggestions for Future Research
REFERENCES
APPENDIX 1 TEXTURE IMAGES FROM BRODATZ ALBUM
Others
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔