Zhang Tongue Image Analysis

1. Auflage 2017
ISBN: 978-981-10-2167-1
Verlag: Springer Nature Singapore
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 335 Seiten

This is the first book offering a systematic description of tongue image analysis and processing technologies and their typical applications in computerized tongue diagnostic (CTD) systems. It features the most current research findings in all aspects of tongue image acquisition, preprocessing, classification, and diagnostic support methodologies, from theoretical and algorithmic problems to prototype design and development of CTD systems. The book begins with a very in-depth description of CTD on a need-to-know basis which includes an overview of CTD systems and traditional Chinese medicine (TCM) in order to provide the information on the context and background of tongue image analysis. The core part then introduces algorithms as well as their implementation methods, at a know-how level, including image segmentation methods, chromatic correction, and classification of tongue images. Some clinical applications based on these methods are presented for the show-how purpose in the CTD research field. Case studies highlight different techniques that have been adopted to assist the visual inspection of appendicitis, diabetes, and other common diseases. Experimental results under different challenging clinical circumstances have demonstrated the superior performance of these techniques. In this book, the principles of tongue image analysis are illustrated with plentiful graphs, tables, and practical experiments to provide insights into some of the problems. In this way, readers can easily find a quick and systematic way through the complicated theories and they can later even extend their studies to special topics of interest. This book will be of benefit to researchers, professionals, and graduate students working in the field of computer vision, pattern recognition, clinical practice, and TCM, as well as those involved in interdisciplinary research.

David Zhang graduated in Computer Science from Peking University. He received his MSc in 1982 and his PhD in 1985 in Computer Science from the Harbin Institute of Technology (HIT). From 1986 to 1988 he was a postdoctoral fellow at Tsinghua University and then an associate professor at the Academia Sinica, Beijing. In 1994 he received his second PhD in Electrical and Computer Engineering from the University of Waterloo, Ontario, Canada. Currently, he is a Chair Professor at the Hong Kong Polytechnic University, where he is the Founding Director of Biometrics Research Centre (UGC/CRC), which has been supported by the Hong Kong SAR Government since 1998. He also serves as Visiting Chair Professor at Tsinghua University and HIT, and Adjunct Professor at Shanghai Jiao Tong University, Peking University, the National University of Defense Technology and the University of Waterloo. So far, he has been published more than 10 books and 400 international journal papers. He was listed as a highly cited researcher in Engineering by Thomson Reuters in 2014 and in 2015, respectively. Professor Zhang is a Croucher senior research fellow, distinguished speaker of the IEEE computer society, and a Fellow of both the IEEE and the IAPR.
Hongzhi Zhang received his Ph.D. degree in computer science and technology from Harbin institute of Technology (HIT), China, in 2007. He is an associate Professor at the School of Computer Science and Technology, HIT, where he has taught for over 15 years. He teaches biomedical image processing and has investigated computerized tongue diagnosis at the Research Center of Perception and Computing. He is a member of  the IEEE, the Chinese Association for Artificial Intelligence (CAAI), and the  China Society of Integrated Traditional Chinese and Western Medicine. His research interests include theoretic approaches to problems in biomedical imaging, biometric image analysis, computer vision, and signal processing. His research has been supported by grants from the National Natural Science Foundation of China. He is the author of more than 70 international journal and conference papers.  
Bob Zhang received his Ph.D. degree in electrical and computer engineering from the University of Waterloo, Waterloo, Canada, in 2011. After graduating from Waterloo, he remained with the Center for Pattern Recognition and Machine Intelligence, and was later a postdoctoral researcher at the Department of Electrical and Computer Engineering at Carnegie Mellon University, Pittsburgh, USA. He is currently an assistant professor in the Department of Computer and Information Science, University of Macau, Taipa, Macau. His research interests focus on medical biometrics, biometrics security, pattern recognition, and image processing. Dr. Zhang is a Technical Committee Member of the IEEE Systems, Man, and Cybernetics Society, an Associate Editor for the International Journal of Image and Graphics, as well as an editorial board member for the International Journal of INFORMATION.

Autoren/Hrsg.

Zhang, David

Zhang, Hongzhi

Zhang, Bob

Inhaltsverzeichnis

1;Preface;5
2;Contents;9
3;Background;16
4;1 Introduction to Tongue Image Analysis;17
4.1;Abstract;17
4.2;1.1 Tongue Inspection for Medical Applications;17
4.3;1.2 Computerized Tongue Diagnosis System;20
4.4;1.3 Research Review on Tongue Image Analysis;21
4.4.1;1.3.1 Tongue Image Acquisition;21
4.4.2;1.3.2 Tongue Image Preprocessing;22
4.4.2.1;1.3.2.1 Color Correction;22
4.4.2.2;1.3.2.2 Image Segmentation;23
4.4.3;1.3.3 Qualitative Feature Extraction;24
4.4.4;1.3.4 Diagnostic Classification;25
4.5;1.4 Issues and Challenges;25
4.5.1;1.4.1 Inconsistent Image Acquisition;26
4.5.2;1.4.2 Inaccurate Color Correction;27
4.5.3;1.4.3 Subjective Tongue Color Extraction and Classification;28
4.6;References;28
5;2 Tongue Images Acquisition System Design;33
5.1;Abstract;33
5.2;2.1 Introduction;33
5.3;2.2 System Framework and Requirement Analysis;36
5.3.1;2.2.1 System Framework;37
5.3.2;2.2.2 Requirement Analysis;38
5.4;2.3 Optimal System Design;41
5.4.1;2.3.1 Illuminant;41
5.4.2;2.3.2 Lighting Condition;42
5.4.3;2.3.3 Imaging Camera;44
5.4.4;2.3.4 Color Correction;46
5.4.5;2.3.5 System Implementation and Calibration;47
5.4.5.1;2.3.5.1 Camera Lens Aperture;48
5.4.5.2;2.3.5.2 Camera Color Balance;49
5.4.5.3;2.3.5.3 Color Correction Model;49
5.5;2.4 Performance Analysis;49
5.5.1;2.4.1 Illumination Uniformity;50
5.5.2;2.4.2 System Consistency;51
5.5.2.1;2.4.2.1 Consecutive Consistency;52
5.5.2.2;2.4.2.2 Intra-run Consistency;52
5.5.2.3;2.4.2.3 Inter-run Consistency;53
5.5.2.4;2.4.2.4 Between-Device Consistency;54
5.5.3;2.4.3 Accuracy;55
5.5.4;2.4.4 Typical Tongue Images;55
5.6;2.5 Summary;56
5.7;References;57
6;Tongue Image Segmentation and Shape Classification;59
7;3 Tongue Image Segmentation by Bi-elliptical Deformable Contour;60
7.1;Abstract;60
7.2;3.1 Introduction;60
7.3;3.2 Bi-elliptical Deformable Template for the Tongue;63
7.3.1;3.2.1 Definitions and Notations;63
7.3.2;3.2.2 The Tongue Template;64
7.3.3;3.2.3 Energy Function for the Tongue Template;65
7.4;3.3 Combined Model for Tongue Segmentation;68
7.4.1;3.3.1 Two Kinds of Template Forces;69
7.4.1.1;3.3.1.1 Linear Template Force (LTF);70
7.4.1.2;3.3.1.2 Elliptical Template Force (ETF);71
7.4.2;3.3.2 Bi-elliptical Deformable Contours;72
7.4.2.1;3.3.2.1 Tongue Segmentation Algorithm;73
7.5;3.4 Experiment Results and Analysis;75
7.6;3.5 Summary;82
7.7;References;82
8;4 A Snake-Based Approach to Automated Tongue Image Segmentation;84
8.1;Abstract;84
8.2;4.1 Introduction;84
8.3;4.2 Automated Segmentation Algorithm for Tongue Images;86
8.3.1;4.2.1 Polar Edge Detection of Tongue Image;86
8.3.2;4.2.2 Filtering and Binarization of the Edge Image;88
8.3.3;4.2.3 Initialization and ACM;89
8.3.4;4.2.4 Summary of the Automated Tongue Segmentation Method;91
8.4;4.3 Experiments and Discussion;93
8.4.1;4.3.1 Evaluation on the Edge Filtering Algorithm;93
8.4.2;4.3.2 Qualitative Evaluation;93
8.4.3;4.3.3 Quantitative Evaluation;95
8.4.3.1;4.3.3.1 Boundary Error Metrics;96
8.4.3.2;4.3.3.2 Area Error Metrics;98
8.5;4.4 Summary;100
8.6;References;100
9;5 Tongue Segmentation in Hyperspectral Images;102
9.1;Abstract;102
9.2;5.1 Introduction;102
9.3;5.2 Setup of the Hyperspectral Device;104
9.4;5.3 Segmentation Framework;105
9.4.1;5.3.1 Hyperspectral Image Calibration;106
9.4.2;5.3.2 Segmentation;107
9.5;5.4 Experiments and Comparisons;109
9.5.1;5.4.1 Criteria of Evaluation;111
9.5.2;5.4.2 Comparison with the BEDC;112
9.6;5.5 Summary;114
9.7;References;114
10;6 Tongue Segmentation by Gradient Vector Flow and Region Merging;116
10.1;Abstract;116
10.2;6.1 Introduction;116
10.3;6.2 Initial Segmentation;117
10.4;6.3 Extraction of Tongue Area;119
10.4.1;6.3.1 Similarity Metric;119
10.4.2;6.3.2 The Extraction of the Tongue Body by Using the MRSM Algorithm;120
10.5;6.4 Experimental Results and Discussions;121
10.5.1;6.4.1 Experimental Results;121
10.5.2;6.4.2 Qualitative Evaluation;122
10.5.3;6.4.3 Quantitative Evaluation;123
10.5.4;6.4.4 Running Time of the Proposed Method;124
10.5.5;6.4.5 Limitations of the Proposed Method;125
10.6;6.5 Summary;125
10.7;References;126
11;7 Tongue Segmentation by Fusing Region-Based and Edge-Based Approaches;127
11.1;Abstract;127
11.2;7.1 Introduction;127
11.3;7.2 Extraction of the ROI to Enhance Robustness;129
11.4;7.3 Combining Region-Based and Edge-Based Approaches;132
11.4.1;7.3.1 Region-Based Approach: Improved MSRM;133
11.4.2;7.3.2 Optimal Edge-Based Approach: Fast Marching;135
11.4.3;7.3.3 The Fusion Approach as a Solution;137
11.5;7.4 Experiments and Comparisons;139
11.5.1;7.4.1 Qualitative Evaluation;139
11.5.2;7.4.2 Quantitative Evaluation;141
11.6;7.5 Summary;142
11.7;References;142
12;8 Tongue Shape Classification by Geometric Features;144
12.1;Abstract;144
12.2;8.1 Introduction;144
12.3;8.2 Shape Correction;145
12.3.1;8.2.1 Automatic Contour Extraction;146
12.3.2;8.2.2 The Length Criterion;146
12.3.3;8.2.3 The Area Criterion;147
12.3.4;8.2.4 The Angle Criterion;148
12.3.5;8.2.5 Correction by Combination;149
12.4;8.3 Feature Extraction;150
12.4.1;8.3.1 The Length-Based Feature;151
12.4.1.1;8.3.1.1 The Length–Width Ratio;151
12.4.1.2;8.3.1.2 The off-Center Ratio;151
12.4.1.3;8.3.1.3 The Radial Line Ratio;152
12.4.2;8.3.2 The Area-Based Feature;152
12.4.2.1;8.3.2.1 The Total Area Ratio;152
12.4.2.2;8.3.2.2 The Triangle Area Ratio;153
12.4.2.3;8.3.2.3 The Top–Bottom Area Ratio;154
12.4.3;8.3.3 The Angle-Based Feature;154
12.5;8.4 Shape Classification;155
12.5.1;8.4.1 Modeling the Classification as a Hierarchy;155
12.5.2;8.4.2 Calculating Relative Weights;157
12.5.3;8.4.3 Calculating the Global Weights;158
12.5.4;8.4.4 Fuzzy Shape Classification;158
12.6;8.5 Experimental Results and Performance Analysis;159
12.6.1;8.5.1 Accuracy of Shape Correction;159
12.6.2;8.5.2 Accuracy of Shape Classification;160
12.7;8.6 Summary;163
12.8;References;163
13;Tongue Color Correction and Classification;165
14;9 Color Correction Scheme for Tongue Images;166
14.1;Abstract;166
14.2;9.1 Introduction;166
14.3;9.2 Color Space for Tongue Analysis;168
14.4;9.3 Color Correction Algorithms;170
14.4.1;9.3.1 Definitions of Algorithms;171
14.4.2;9.3.2 Evaluation of the Correction Algorithms;172
14.4.3;9.3.3 Experiments and Results;173
14.4.3.1;9.3.3.1 Imaging Device;173
14.4.3.2;9.3.3.2 Dataset;173
14.4.3.3;9.3.3.3 Parameters Setting;174
14.4.3.4;9.3.3.4 Experimental Results on the Colorchecker;175
14.4.3.5;9.3.3.5 Experimental Results on Tongue Images;176
14.4.3.6;9.3.3.6 Discussion;178
14.5;9.4 Experimental Results and Performance Analysis;178
14.5.1;9.4.1 Color Correction by Different Cameras;179
14.5.2;9.4.2 Color Correction Under Different Lighting Conditions;180
14.5.3;9.4.3 Performance Analysis;182
14.5.4;9.4.4 Correction on Real Tongue Images;183
14.6;9.5 Summary;185
14.7;References;186
15;10 Tongue Colorchecker for Precise Correction;188
15.1;Abstract;188
15.2;10.1 Introduction;188
15.3;10.2 Tongue Color Space;190
15.4;10.3 Determination of the Number of Colors;192
15.4.1;10.3.1 Setting for Number Deciding Experiment;193
15.4.1.1;10.3.1.1 Training and Testing Dataset;193
15.4.1.2;10.3.1.2 Experimental Implementation;194
15.4.1.3;10.3.1.3 Configuration for Stability Test;195
15.4.2;10.3.2 Results of Number Determination;196
15.4.2.1;10.3.2.1 Obtained Minimum Sufficient Number;196
15.4.2.2;10.3.2.2 Results of the Stability Test;197
15.5;10.4 Optimal Colors Selection;199
15.5.1;10.4.1 Objective Function;199
15.5.2;10.4.2 Selection Algorithms;201
15.5.2.1;10.4.2.1 The Greedy Method;201
15.5.2.2;10.4.2.2 The Clustering-Based Method;202
15.5.2.3;10.4.2.3 Selection the Color Space;203
15.6;10.5 Experimental Results and Performance Analysis;204
15.6.1;10.5.1 Experimental Configuration;204
15.6.1.1;10.5.1.1 Training and Testing Dataset;204
15.6.1.2;10.5.1.2 Flowchart of the Experiment;204
15.6.2;10.5.2 Parameter Optimization;205
15.6.2.1;10.5.2.1 Color Space;205
15.6.2.2;10.5.2.2 Selection Method;207
15.6.2.3;10.5.2.3 Diversity Measurement;208
15.6.2.4;10.5.2.4 Distance Measure;209
15.6.2.5;10.5.2.5 Performance Comparison;211
15.7;10.6 Summary;213
15.8;References;213
16;11 Tongue Color Analysis for Medical Application;215
16.1;Abstract;215
16.2;11.1 Introduction;215
16.3;11.2 Tongue Image Acquisition Device and Dataset;217
16.4;11.3 Tongue Color Gamut and Color Features Extraction;218
16.4.1;11.3.1 Tongue Color Gamut;218
16.4.2;11.3.2 Tongue Color Features;220
16.5;11.4 Results and Discussion;223
16.5.1;11.4.1 Healthy Versus Disease Classification;223
16.5.2;11.4.2 Typical Disease Analysis;224
16.6;11.5 Summary;230
16.7;References;231
17;12 Statistical Analysis of Tongue Color and Its Applications in Diagnosis;232
17.1;Abstract;232
17.2;12.1 Introduction;232
17.3;12.2 Tongue Image Acquisition and Database;234
17.3.1;12.2.1 Tongue Image Acquisition Device;234
17.3.2;12.2.2 Color Correction of Tongue Images;235
17.3.3;12.2.3 Tongue Image Database;237
17.4;12.3 Tongue Color Distribution Analysis;238
17.4.1;12.3.1 Tongue Color Gamut: Generation and Modeling;238
17.4.2;12.3.2 Tongue Color Centers;246
17.4.3;12.3.3 Distribution of Typical Image Features;249
17.5;12.4 Color Feature Extraction;251
17.5.1;12.4.1 Tongue Color Feature Vector;252
17.5.2;12.4.2 Typical Samples of Tongue Color Representation;252
17.6;12.5 Summary;255
17.7;References;255
18;13 Hyperspectral Tongue Image Classification;258
18.1;Abstract;258
18.2;13.1 Introduction;258
18.3;13.2 Hyperpectral Images for Tongue Diagnosis;260
18.4;13.3 The Classifier Applied to Hyperspectral Tongue Images;261
18.4.1;13.3.1 Linear SVM: Linearly Separable;261
18.4.2;13.3.2 Linear SVM: Linearly Non-separable;262
18.4.3;13.3.3 Non-linear SVM;263
18.5;13.4 Experimental Results and Performance Analysis;264
18.5.1;13.4.1 Comparing Linear and Non-linear SVM, RBFNN, and K-NN Classifiers;264
18.5.2;13.4.2 Evaluating the Diagnostic Performance of SVM;265
18.6;13.5 Summary;267
18.7;References;268
19;Tongue Image Analysis and Diagnosis;269
20;14 Computerized Tongue Diagnosis Based on Bayesian Networks;270
20.1;Abstract;270
20.2;14.1 Introduction;270
20.3;14.2 Tongue Diagnosis Using Bayesian Networks;271
20.4;14.3 Quantitative Pathological Features Extraction;274
20.4.1;14.3.1 Quantitative Color Features;274
20.4.2;14.3.2 Quantitative Texture Features;275
20.5;14.4 Experimental Results;277
20.5.1;14.4.1 Several Issues;278
20.5.2;14.4.2 Bayesian Network Classifier Based on Textural Features;279
20.5.3;14.4.3 Bayesian Network Classifier Based on Chromatic Features;280
20.5.4;14.4.4 Bayesian Network Classifier Based on Combined Features;281
20.6;14.5 Summary;284
20.7;References;284
21;15 Tongue Image Analysis for Appendicitis Diagnosis;286
21.1;Abstract;286
21.2;15.1 Introduction;286
21.3;15.2 Chromatic and Textural Features for Tongue Diagnosis;287
21.3.1;15.2.1 The Image of the Tongue of a Patient with Appendicitis;287
21.3.2;15.2.2 Quantitative Features of the Color of the Tongue;288
21.3.3;15.2.3 Quantitative Features of the Texture of the Tongue;288
21.4;15.3 Identification of Filiform Papillae;289
21.4.1;15.3.1 Typical Figures and Statistics of Filiform Papillae;289
21.4.2;15.3.2 Filter for Filiform Papillae;291
21.5;15.4 Experimental Results and Analysis;292
21.5.1;15.4.1 Evaluation Basis for Diagnosis;293
21.5.2;15.4.2 Performance of Metrics for Color;293
21.5.3;15.4.3 Performance of Textural Metrics;295
21.5.4;15.4.4 Performance of the FPF;296
21.6;15.5 Summary;298
21.7;References;298
22;16 Diagnosis Using Quantitative Tongue Feature Classification;299
22.1;Abstract;299
22.2;16.1 Introduction;299
22.3;16.2 Tongue Image Samples;300
22.4;16.3 Quantitative Chromatic and Textural Measurements;300
22.5;16.4 Feature Selection;302
22.6;16.5 Results and Analysis;302
22.7;16.6 Summary;303
22.8;References;305
23;17 Detecting Diabetes Mellitus and Nonproliferative Diabetic Retinopathy Using CTD;306
23.1;Abstract;306
23.2;17.1 Introduction;306
23.3;17.2 Capture Device and Tongue Image Preprocessing;308
23.4;17.3 Tongue Color Features;309
23.4.1;17.3.1 Tongue Color Gamut;309
23.4.2;17.3.2 Color Feature Extraction;310
23.5;17.4 Tongue Texture Features;314
23.6;17.5 Tongue Geometric Features;316
23.7;17.6 Numerical Results and Discussion;320
23.7.1;17.6.1 Healthy Versus DM Classification;320
23.7.2;17.6.2 NPDR Versus DM-Sans NPDR Classification;324
23.8;17.7 Summary;326
23.9;References;327
24;Book Recapitulation;329
25;18 Book Review and Future Work;330
25.1;Abstract;330
25.2;18.1 Book Recapitulation;330
25.3;18.2 Future Work;331
26;Index;333