Admin
مدير المنتدى
عدد المساهمات : 18727
التقييم : 34715
تاريخ التسجيل : 01/07/2009
الدولة : مصر
العمل : مدير منتدى هندسة الإنتاج والتصميم الميكانيكى
 |  موضوع: كتاب Digital Image Processing and Analysis Applications with MATLAB and CVIPtools الثلاثاء 19 أكتوبر 2021, 1:07 am | |
| 
أخواني في الله
أحضرت لكم كتاب
Digital Image Processing and Analysis Applications with MATLAB and CVIPtools
Third Edition
Scott E Umbaugh
و المحتوى كما يلي :
Contents
Preface
Acknowledgments
Author
Section I Introduction to Digital Image Processing and Analysis
1 Digital Image Processing and Analysis
1.1 Overview
1.2 Image Analysis and Computer Vision
1.3 Image Processing and Human Vision.
1.4 Key Points
Exercises
Further Reading
References
2 Digital Image Processing Systems , ....
2.1 Digital Imaging Systems Overview
2.2 Image Formation and Sensing
2.2.1 Visible Light Imaging
2.2.2 Imaging outside the Visible Range of the EM Spectrum
2.2.3 Acoustic Imaging
2.2.4 Electron Imaging
2.2.5 Laser Imaging
2.2.6 Computer-Generated Images
2.3 The CVIPtools Software Environment
2.3.1 CVIPtools GUI Main Window
2.3.2 Image Viewer
2.3.3 Analysis Window
2.3.4 Enhancement Window
2.3.5 Restoration Window
2.3.6 Compression Window
2.3.7 Utilities Window..,..
2.3.8 Help Window
2.3.9 Development Tools
2.4 Image Representation
2.4.1 Binary Images
2.4.2 Grayscale Images
2.4.3 Color Images.....
2.4.4 Multispectral Images
2.4.5 Digital Image File Formats
2.5 Key Points
Exercises
Supplementary Exercises
Further Reading...,..,.,...
References
viiviii Contents
Section II Digital Image Analysis and Computer Vision
3 Introduction to Digital Image Analysis..
Introduction
3.1.1 Overview
3.1.2 System Model
3.2 Preprocessing
3.2.1 Region of Interest (ROI) Image Geometry
3.2.2 Arithmetic and Logic Operations
3.2.3 Spatial Filters
3.2.4 Image Quantization
3.3 Binary Image Analysis .... .. ...
3.3.1 Basic Image Thresholding
3.3.2 Connectivity and Labeling..,,,,,,,,.,,,,
3.3.3 Basic Binary Object Features
3.3.4 Binary Object Classification
3.4 Key Points. ,
Exercises
Supplementary Exercises
Further Reading
References
4 Segmentation and Edge/Line Detection
Introduction and Overview.
4.2 Edge/Line Detection
4.2.1 Gradient Operators
4.2.2 Compass Masks .,
4.2.3 Advanced Edge Detectors ..
4.2.4 Edges in Color Images
4.2.5 Edge Detector Performance
4.2.6 Hough Transform
4.2.6.1
4.2.7 Corner Detection.,...
4.3 Segmentation
4.3.1 Region Growing and Shrinking
4.3.2 Clustering Techniques
4.3.3 Boundary Detection
4.3.4 Combined Segmentation Approaches
4.3.5 Morphological Filtering
4.4 Key Points.
Exercises
Supplementary Exercises
Further Reading
References
CVIPtools Parameters for the Hough Transform 161
5 Discrete Transforms
5.1 Introduction and Overview
5.2 Fourier Transform ......
5.2.1 The One-Dimensional Discrete Fourier Transform .
5.2.2 The Two-Dimensional Discrete Fourier Transform .
5.2.3 Fourier Transform Properties
5.2.3.1 Linearity
5.2.3.2 Convolution
5.2.3.3 Translation
.240Contents ix
5.2.3.4 Modulation.
5.2.3.5 Rotation
d.2.3.6 Periodicity .
5.2.3.7 Sampling and Aliasing.
5.2.4 Displaying the Discrete Fourier Spectrum
5.3 Discrete Cosine Transform
5.4 Discrete Walsh-Hadamard Transform.....
5.5 Discrete Haar Transform
5.6 Principal Components Transform
5.7 Filtering
5.7.1 Low-Pass Filters., ...
5.7.2 High-Pass Filters
5.7.3 Band-pass and Band-reject Filters
5.8 Discrete Wavelet Transform
5.9 Key Points
Exercises
Supplementary Exercises
Further Reading
References
6 Feature Analysis and Pattern Classification
Introduction and Overview ....
6.2 Feature Extraction ,,.,,,.,....,....,,,,.,,,,.,,,,,,,,,,,,,.
6.2.1 Shape Features ....
6.2.2 Histogram Features
6.2.3 Color Features ....
6.2.4 Spectral Features.,....,,,,.,,,,.,,,.,,,,,
6.2.5 Texture Features ....
6.2.6 Region-Based Features: SIFT/SURF/GIST..
6.2.7 Feature Extraction with CVIPtools
6.3 Feature Analysis
6.3.1 Feature Vectors and Feature Spaces,,.,.,.. ....
6.3.2 Distance and Similarity Measures
6.3.3 Data Preprocessing ....».,
6.4 Pattern Classification
6.4.1 Algorithm Development: Training and Testing Methods
6.4.2 Classification Algorithms and Methods
6.4.3 Cost/Risk Functions and Success Measures
6.4.4 Pattern Classification with CVIPtools
6.5 Key Points..,.,,.,,,,.,
Exercises —
Supplementary Exercises
Further Reading
References
Section III Digital Image Processing and Human Vision
7 Digital Image Processing and Visual Perception
7.1 Introduction and Overview
7.2 Human Visual Perception
7.2.1 The Human Visual System
7.2.2 Spatial Frequency Resolution
7.2.3 Brightness Adaptation
,370x Contents
7.2.4 Temporal Resolution
7.2.5 Perception and Illusion
7.3 Image Fidelity Criteria
7.3.1 Objective Fidelity Measures..
7.3.2 Subjective Fidelity Measures.
7.4 Key Points,.,
Exercises
Supplementary Exercises
Further Reading
References
8 Image Enhancement
Introduction and Overview
8.2 Gray-Scale Modification
8.2.1 Mapping Equations
8.2.2 Histogram Modification
8.2.3 Adaptive Contrast Enhancement
8.2.4 Color
8.3 Image Sharpening
8.3.1 High-Pass Filtering
8.3.2 High-Frequency Emphasis
8.3.3 Directional Difference Filters
8.3.4 Homomorphic Filtering
8.3.5 Unsharp Masking
8.3.6 Edge Detector-Based Sharpening Algorithms
8.4 Image Smoothing
8.4.1 Frequency Domain Low-Pass Filtering............
8.4.2 Convolution Mask Low-Pass Filtering....,,...
8.4.3 Nonlinear Filtering
8.5 Key Points..,.,,.,,,,.,
Exercises —
Supplementary Exercises
Further Reading..,,,,,
References
9 Image Restoration and Reconstruction
9.1 Introduction and Overview
9.1.1 System Model
9.2 Noise Models
9.2.1 Noise Histograms
9.2.2 Periodic Noise.,....,....,
9.2.3 Estimation of Noise
9.3 Noise Removal Using Spatial Filters,,,,,,,,,,
9.3.1 Order Filters
9.3.2 Mean Filters
9.3.3 Adaptive Filters
9.4 The Degradation Function ,,,.,,
9.4.1 The Spatial Domain: The Point Spread Function
9.4.2 The Frequency Domain: The Modulation/Optical Transfer Function
9.4.3 Estimation of the Degradation Function
9.5 Frequency Domain Filters
9.5.1 Inverse Filter
9.5.2 Wiener Filter
9.5.3 Constrained Least Squares Filter
9.5.4 Geometric Mean Filters.
. 521Contents xi
9.5.5 Adaptive Filtering..
9.5.6 Band-pass, Band-reject, and Notch Filters
9.5.7 Practical Considerations
9.6 Geometric Transforms
9.6.1 Spatial Transforms. HWH«W.WWHWWI.W
9.6.2 Gray-Level Interpolation
9.6.3 The Geometric Restoration Procedure —
9.6.4 Geometric Restoration with CVIPtools
9.7 Image Reconstruction —......
9.7.1 Reconstruction Using Backprojections
9.7.2 The Radon Transform
9.7.3 The Fourier-Slice Theorem and Direct Fourier Reconstruction
9.8 Key Points ..........
Exercises , ,
Supplementary Exercises
Further Reading , ,
References
10 Image Compression
10.1 Introduction and Overview
10.1.1 Compression System Model
10.2 Lossless Compression Methods
10.2.1 Huffman Coding
10.2.2 Run-Length Coding
10.2.3 Lempel-Ziv-Welch Coding............
10.2.4 Arithmetic Coding
10.3 Lossy Compression Methods
10.3.1 Gray-Level Run-Length Coding
10.3.2 Block Truncation Coding
10.3.3 Vector Quantization
10.3.4 Differential Predictive Coding.,,,,,,
10.3.5 Model-based and Fractal Compression
10.3.6 Transform Coding
10.3.7 Hybrid and Wavelet Methods
10.4 Key Points
Exercises
Supplementary Exercises
Further Reading
References
Section IV Application Development with the Matlab
CVIP Toolbox and CVIPtools
11 Matlab CVIP Toolbox and CVIPlab
11.1 The Matlab CVIP Toolbox
11.1.1 CVIP Toolbox Function Categories ..
11.1.1.1 Arithmetic and Logic
11.1.1.2 Band
11.1.1.3 Color ..,,
11.1.1.4 Conversion of Image Files
11.1.1.5 Display
11.1.1.6 Edge/Line Detection
11.1.1.7 Geometry...,,,
.632xii Contents
11.1.1.8 Histogram
11.1.1.9 Mapping
11.1.1.10 Morphological „
11.1.1.11 Noise
11.1.1.12 Objective Fidelity Metrics
11.1.1.13 Pattern Classification
11.1.1.14 Segmentation
11.1.1.15 Spatial Filters
11.1.1.16 Transform
11.1.1.17 Transform Filters...............
11.1.2 Help Files
11.1.3 M-Files
11.2 CVIPlab for Matlab
11.2.1 Vectorization
11.2.2 Using CVIPlab for Matlab
11.2.3 Adding a Function ..........
11.2.4 A Sample Batch Processing M-File...
11.2.5 VIPM File Format
11.3 CVIPlab for C Programming
11.3.1 Toolkit, Toolbox Libraries, and Memory Management in C/C++
11.3.2 Compiling and Linking CVIPlab with Visual Studio
11.3.3 The Mechanics of Adding a Function with Visual Studio .............
11.3.4 Using CVIPlab in the Programming Exercises
11.3.5 Image Data and File Structures
11.4 CVIP Projects
11.4.1 Digital Image Analysis and Computer Vision Projects
11.4.1.1 Example Project Topics
11.4.2 Digital Image Processing and Human Vision Projects
11.4.2.1 Example Project Topics
Further Reading
References
12 Application Development
12.1 Introduction and Overview
12.2 CVIP Algorithm Test and Analysis Tool
12.2.1 Overview and Capabilities..,,,.,,,,,,.,.,,.,.,..,,
12.2.2 How to Use CVIP-ATAT,.
12.2.2.1 Running CVIP-ATAT..,,., ....
12.2.2.2 Creating a New Project....
12.2.2.3 Inserting Images
12.2.2.4 Inputting an Algorithm
12.2.2.5 Performing an Algorithm Test Run
12.2.2.6 Comparing Images..
12.2.3 Application Development Example with Fundus Images
12.2.3.1 Introduction and Overview
12.2.3.2 The New Algorithm....,,.,
12.2.3.3 Conclusion..
12.3 CVIP Feature Extraction and Pattern Classification Tool
12.3. 1 Overview and Capabilities
12.3.2 How to Use CVIP-FEPC
12.3.2.1 Running CVIP-FEPC
12.3.2.2 Creating a New Project..,.,,.,...
12.3.2.3 Entering Classes in CVIP-FEPC
12.3.2.4 Adding Images and Associated Classes
12.3.2.5 Applying Feature Extraction and Pattern Classification
.691Contents xiii
12.3.2.6 Running a Single Test with Training and Test Sets
12.3.2.7 The Result File
12.3.2.8 Running a Leave-One-Out Test in Combinatoric Mode
12.3.3 Application Development Example with Veterinary Thermographic Images
12.3.3.1 Introduction and Overview
12.3.3.2 Setting up Experiments
12.3.3.3 Running the Experiments and Analyzing Results
12.3.3.4 Conclusion
12.4 Automatic Mask Creation for Feline Hyperthyroidism from Veterinary Thermograms
using the Matlab CVIP Toolbox
12.4.1 Introduction
12.4.2 Matlab CVIP Toolbox
12.4.3 Automatic Creation of Masks for Veterinary Thermographic Images
12.4.3.1 Background
12.4.3.2 Materials Required
12.4.3.3 Methods
12.4.3.4 Algorithm Development and Testing. 705
12.4.4 Results 706
12.4.5 Summary and Conclusions
Acknowledgments
References
12.5 Thermographic Image Analysis for Detection of Anterior Cruciate Ligament
Rupture in Canines
12.5.1 Introduction and Overview
12.5.2 Materials and Methods
12.5.2.1 Image Database
12.5.2.2 Image Preprocessing
12.5.2.3 Feature Selection and Extraction
12.5.2.4 Data Normalization and Pattern Classification
12.5.3 Results and Discussion
12.5.4 Conclusion
Acknowledgments
References
12.6 Thermographic Image Analysis for the Detection of Canine Bone Cancer
12.6.1 Introduction
12.6.2 Material and Methods
12.6.2.1 Experimental Animals
12.6.2.2 Digital Infrared Thermal Imaging System
12.6.2.3 Thermographic Images
12.6.2.4 Software Tools Used
12.6.2.5 Mask Creation
12.6.2.6 Color Normalization
12.6.2.7 Feature Selection and Extraction
12.6.2.8 Data Normalization and Pattern Classification
12.6.2.9 Experimental Methods
12.6.3 Results and Discussion
12.6.4 Summary and Conclusion
Acknowledgments
References
12.7 A New Algorithm for Blood Vessel Segmentation in Retinal Images Developed
with CVIP-ATAT
12.7.1 Introduction
12.7.2 Materials
12.7.3 Methods
12.7.4 Results
725xiv Contents
12.7.5 Future Work M ,HW». HWHWH«H~
12.7.6 Summary and Conclusion.
Acknowledgments
References
12.8 Automatic Mask Creation and Feature Analysis for Detection of IVDD in Canines
12.8.1 Introduction
12.8.2 Background
12.8.3 Materials and Methods
12.8.3.1 Thermographic Images
12.8.3.2 Masks
12.8.3.3 Programs and Methods .............
12.8.3.4 Experimental Process
12.8.3.5 Input Images .............
12.8.3.6 Extract Band
12.8.3.7 Binary Threshold
12.8.3.8 Morphological Filtering.
.730
.730
12.8.4 Results .732
12.8.5 Conclusion
Acknowledgments ............
References
12.9 Skin Lesion Classification Using Relative Color Features ............
12.9.1 Introduction and Project Overview
12.9.2 Materials and Methods ............
12.9.2.1 Image Database
12.9.2.2 Creation of Relative Color Images ........
12.9.2.3 Segmentation and Morphological Filtering
12.9.2.4 Feature Extraction ............
12.9.2.5 The Lesion and Object Feature Spaces
12.9.2.6 Statistical Models — ........
12.9.3 Experiments and Data Analysis
12.9.3.1 Lesion Feature Space...... ........
12.9.3.2 Object Feature Space...............
12.9.4 Conclusions ............
Acknowledgments...
References ............
12.10 Automatic Segmentation of Blood Vessels in Retinal Images
12.10.1 Introduction and Overview ............
12.10.2 Materials and Methods
12.10.3 Results ............
12.10.4 Postprocessing with Hough Transform and Edge Linking.
12.10.5 Conclusion
Acknowledgments...
References ............
12.11 Classification of Land Types from Satellite Images Using Quadratic Discriminant
Analysis and Multilayer Perceptrons ............
12.11.1 Introduction and Overview
12.11.2 Data Reduction and Feature Extraction ....................
12.11.3 Object Classification.....
12.11.4 Results ............
12.11.5 Conclusion
Acknowledgments ............
References
12.12 Watershed-based Approach to Skin Lesion Border Segmentation. ............
12.12.1 Introduction
. 760Contents xv
12.12.2 Materials and Methods
12.12.2.1 Preprocessing
12.12.2.2 The Watershed Algorithm
12.12.2.3 Object Histogram Merging , ,
12.12.2.4 Noise Removal
12.12.2.5 B-Spline Border Smoothing
12.12.2.6 Error Estimating.,,,,,,,,,,,,,,
12.12.3 Experiments, Results and Conclusions
Acknowledgments
References
12.13 Faint Line Defect Detection in Microdisplay (CCD) Elements
12.13.1 Introduction and Project Overview „
12.13.2 Design Methodology
12.13.3 The Line-Detection Algorithm „ „
12.13.3.1 Preprocessing,,,.,,,,,,,,,,,,,,
12.13.3.2 Edge Detection
12.13.3.3 Analysis of the Hough Space
12.13.4 Results and Discussion
12.13.5 Summary and Conclusion..
Acknowledgments...
References
12.14 Melanoma and Seborrheic Keratosis Differentiation Using Texture Features
12.14.1 Introduction and Overview
12.14.2 Materials and Methods
12.14.3 Texture Analysis Experiments. IIWHWWMHW«wi.4
12.14.4 Results and Discussion
12.14.5 Conclusion
Acknowledgments.....,,.,.,,
References .................
12.15 Compression of Color Skin Tumor Images with Vector Quantization
12.15.1 Introduction and Project Overview
12.15.2 Materials and Methods
12.15.2.1 Compression Schemes
12.15.2.2 Subjective Evaluation of the Images
12.15.2.3 Objective Measurement of the Images .................
12.15.3 Compression Schemes
12.15.3.1 Preprocessing and Transforms.
12.15.3.2 Vector Quantization..,,,,...,,.,.,,
12.15.3.3 Postprocessing
12.15.4 Results and Analysis
12.15.4.1 Results and Analyses for the Schemes with Compression Ratio 4:1..
12.15.4.2 Results and Analyses for the Schemes with Compression Ratio 8:1..
12.15.4.3 Results and Analyses for the Schemes with Compression Ratio 14:1
12.15.4.4 Results and Analyses for the Schemes with Compression Ratio 20:1
12.15.4.5 Comprehensive Analysis of the Four Compression Ratios..................
12.15.5 Conclusions and Future Work
Acknowledgments — ............ ...
References
12.16 Embedded Application: Image Sensor Power Requirements for Vole Detection
Application with CVIPtools and OpenCV.
12.16.1 Introduction
12.16.2 Common Vole Detection
12.16.3 Vole Detection Algorithm...
12.16.4 The Camera Sensor..,,..,
.804xvi Contents
12.16.5 Conclusions
Acknowledgments..
References
12.17 Gabor Filters for Pathology Classification in Veterinary Thermograms ....
12.17.1 Overview
12.17.2 Background
12.17.2.1 Gabor F i l t e r ,
12.17.2.2 Feature Extraction ...
12.17.2.3 Classification
12.17.3 Results and Discussion
12.17.3.1 Bone Cancer: Elbow/Knee—Anterior
12.17.3.2 Bone Cancer: Elbow/Knee—Lateral
12.17.3.3 Bone Cancer: Wrist-Lateral
12.17.3.4 Feline Hyperthyroid
12.17.3.5 ACL
12.17.4 Future Work
Acknowledgments
References
12.18 Thermography-Based Prescreening Software Tool for Veterinary Clinics
12.18.1 Introduction
12.18.2 Clinical Application Development
12.18.2.1 The Image Database.,,..,.,
12.18.2.2 Algorithm Database,,,,,,
12.18.2.3 Process Flow ,,
12.18.2.4 Graphical User Interface (GUI)
12.18.3 Results and Discussion
12.18.4 Summary and Conclusions
Acknowledgments.,...,....,,
References
Appendices
Appendix A: Installing and Updating CVIPtools
Appendix B: Installing and Updating the Matlab CVIP Toolbox
Appendix C: CVIPtools Software Organization
Appendix D: CVIPtools C Functions
Appendix E: Common Object Module (COM) Functions - cviptools.dll
Appendix F: Matlab CVIP Toolbox Functions
Appendix G: CVIP Resources
Index .861
861
Index
Note: The letters ‘t’ and ‘f’ followed by numbers represents ‘table’ and ‘figures’ respectively�
A
Aberrations, 22
ACE filter, 418
Acoustic imaging, 26
Acoustical (sound) energy, 17
Activation function, 331
Adaptive contrast enhancement (ACE) filters,
415, 419f, 634
Adaptive contrast filter 2 (ACE2), 420f
Adaptive filter, 483, 497–508; see also Kuwahara filter
Adaptive filtering, 523
Adaptive median filter and standard median filter, 504f
Adding a function with visual studio, mechanics,
659–662
Adding a new function to CVIPlab, 660f
Adding an image capture program to CVIPlab, 659f
Advanced edge detectors, 128–139
with Gaussian noise, 157f
with salt and pepper noise, 156f
Affine transformations, 605
Algorithm development, 327
Alpha-trimmed filter, 489f–490f
Amplitude-modulated (AM) phase shift, 30
Analysis window, 35
AND method, 203f
Anisotropic diffusion (AD) filter, 449–450, 450f–451f
Anti-aliasing filter, 93f
Application libraries, 655
Apply button, 35
Arithmetic coding, 582–583, 582f
Arithmetic mean filter, 489, 491f
Arithmetic operations, 76–80
addition, 76
division, 76
multiplication, 76
subtraction, 76
Artificial neural networks (ANNs), 330
Aspect ratio, 15, 298
for high-definition television, 15f
for standard-definition television, 15f
Atmospheric turbulence degradation model, 513f
Automatic gain control (AGC), 370f
Automatic mask creation, 703
automatic creation of masks, 703
Matlab CVIP toolbox, 703
algorithm development and testing, 705–706
background, 703
materials required, 703–704
methods, 704–705
results, 707–709
Automatic mask creation and feature analysis, 727
background, 727–728
materials and methods, 728
binary threshold, 730
experimental process, 729
extract band, 730
input images, 729–730
masks, 728
morphological filtering, 730–732
programs and methods, 728–729
results, 732
thermographic images, 728
Automatic segmentation of blood
vessels in retinal images, 744
introduction and overview, 744–745
materials and methods, 745–746
postprocessing with hough transform and edge
linking, 748–751
Average value thresholding
image after Sobel edge detector, 179f
original image, 179f
Sobel image, 179f
unimodal histogram, 179f
Axis of least second moment, 99f
B
Background subtraction, 78
Backprojection, 539f
Band, 631
Band-pass (BP) filters, 267–271, 270f–271f, 523–526, 525f–526f
Basic binary object features, 97–100
Basic block truncation coding (BTC), 591f–592f
Basic image thresholding, 93–95
Basis images set, 228f
Basis vectors and images, 226f
Bilinear interpolation, 76, 531
BIN format, 55
Binary dilation, 186f
Binary erosion, 187f
Binary image analysis, 93–109
Binary images, 45–46
binary text, 46t
edge detection, 46t
image by threshold operation, 46t
threshold operation, 46t
Binary object classification, 101–109
Binary opening, 188f
Binary threshold, 141f
Bit allocation, 606
Bit plane images, 570f
Bit plane run length coding, 579f862 Index
Bitmap images, 55
Bits per pixel, 566
Blind spot, 362
Block truncation coding, 585–589
Block-by-block processing, 523
Blocking artifact, 523
Blocking effect, 523
Blood vessel segmentation in retinal images, 723
future work, 725
materials, 723
methods, 723–725
Blue cones, 362
Blur (PSF) masks, 511f
Blur circle, 21f
Blurry, noisy composite image, 106f
Bogus lines, 371
Boie–Cox algorithm, 133, 137f
Boundary detection, 176–182
Brightness adaptation, 370–371, 370f
false contours, 371
small curve, 371
subjective brightness, 371
Brightness constancy, 375, 378f
Brittlestar, 29f
Building the project, 658f
Butterworth filter, 262
C
Camera interface specifications, 16t
Camera link, 16
Cancel button, 35
Canny algorithm, 131, 137f
Canny parameters, 162
Central-slice theorem, see Fourier-slice theorem
Cervenka and Charvat method, 632
Cervenka and Charvatmultispectral image detector, 144f
Charge-coupled device (CCD), 23
Chessboard distance, 146
Chiari malformation, 24
Chromaticity coordinates (XYZ), 631
CIE La*b* (LAB), 631
CIE Lu*v* (LUV), 631
Circle and ellipse, XOR, 104f
Circular convolution, 272, 273f
City block, 319
City block distance, 146
Classification algorithms and methods,
328–332
Closing operation, 185, 186f, 189f
Clustering algorithm, 593
Clustering techniques, 168–176
CMOS image sensors, 23
Coding redundancy, 567
Coherent light, 29
Color, 423–431
Color contrast enhancement algorithm
compared to histogram equalization,
430f, 431f
flowchart, 429f
Color edge detection
in HSV Space, 142f
in RGB Space, 143f
Color features, 305–306
Color image representation, 48f
Colorimages, 47–54
Color model, 47
Color perception, 53f
Color pixel vector, 47
Color skin tumor images with vector quantization, 783
compression schemes, 786
postprocessing, 790–791
preprocessing and transforms, 786–787
vector quantization, 787–790
materials and methods, 784
compression schemes, 784
objective measurement of the images, 785
subjective evaluation of the images, 785
results and analysis, 791–797
Color space, 47
Color transform, 47
Color triangle, 174f
Color video standards
NTSC, 13
PAL, 13
SECAM, 13
Combined segmentation approaches, 182–183
Common filters for filtering projections, 541f
Common object module (COM), 32
Comparison tests, 381
Compass masks, 128
Compiling and linking CVIPlab with visual studio,
656–658
Compiling and running CVIPlab, 658f
Complement image—NOT operation, 83
Complementary metal-oxide- semiconductor (CMOS), 23
Complex numbers, 235f
Compression ratio, 565
Compression system model, 568–572, 568f
Compression window, 38
Compressor, 568, 569f
Computational intelligence-based methods, 523
Computed tomography (CT), 538
Computer-generated images, 30
error image, 31f
Fourier transform spectrum image of an ellipse, 31f
graphics image of a simple 3D hand, 30f
graphics image of an insect, 30f
image of a butterfly, 31f
X-ray image of a hand, 31f
Computer graphics, 55
Computer vision and image processing tools (CVIPtools),
13, 32
Computer vision system, 3
Computerized tomography (CT), 24
Cones, 361f, 362f
Connect distance (max), 161
Connectivity and labeling, 95–97
Constrained least squares (CLS)filter, 520–521, 522f
Contra-harmonic mean (CHM) filter, 491, 494Index 863
Contrast stretching
image enhanced, 9f
image with poor contrast, 9f
Convolution mask low-pass filtering, 443
Convolution mask, 72
Convolution process, 72–73, 75f
Convolution theorem, 272
Corner detection, 162–165
Correlation, 310
Correlation coefficient, 319
Correlation factor, 319
Cosine spectrum, 276f
Cosine symmetry, 249f
Cost/risk functions and success measures, 332–335
Creation of image by backprojections, 540f
Crop process, 72
Custom remap curvebutton, 426
Cutoff frequency, 260
CVIP algorithm test and analysis tool, 673
application development example with fundus
images, 681
introduction and overview, 681–683
new algorithm, 683–687
CVIP-ATAT, 674
overview and capabilities, 673–674
comparing images, 681
creating a new project, 674–677
inputting an algorithm, 678
performing an algorithm test run, 678–681
running, 674
CVIP Feature Extraction and Pattern Classification Tool, 688
application development example, 698
introduction and overview, 698
running the experiments and analyzing results, 699
setting up experiments, 698–699
CVIP-FEPC, 688
overview and capabilities, 688–689
adding images and associated classes, 689–691
applying feature extraction and pattern
classification, 691
creating a new project, 689
entering classes in CVIP-FEPC, 689
result file, 696
running, 689
running a leave-one-out test in combinatoric mode,
696–698
running a single test with training and test sets,
691–695
CVIP function information, 33
CVIPlab C program, 651
CVIPlab�c, 651
CVIPlab�h, 651
threshold_lab�c, 651
CVIPlab for Matlab, 638
adding a function, 646–647
CVIPlab for C programming, 650–654
sample batch processing M-file, 647–648
toolkit/toolbox libraries/memory management in
C/C++, 655
usingCVIPlab for Matlab, 643–646
vectorization, 642–643
VIPM file format, 649
adding a function with visual studio, mechanics,
659–662
compiling and linking CVIPlab with visual studio,
656–658
image data and file structures, 664–669
usingCVIPlab in the programming exercises, 663
CVIP Matlabhelp window, 44f–45f
CVIP Matlabtoolbox, 4
CVIP projects, 669
digital image analysis and computer vision projects,
669–670
digital image processing and human vision
projects, 671
example project topics, 670
CVIP toolbox help, 637f
CVIPtools analysis window, 36
drop-down menu, 36f
with edge/line detection tab, 36f
CVIPtools software environment, 32
analysis window, 35
compression window, 38–39
CVIPtools GUI main window, 32–34
development tools, 40
enhancement window, 35
help window, 40
image viewer, 34–35
restoration window, 36–38
utilities window, 40
CVIPlab command window, 645f
CVIPlab figure display window, 645f
CVIPlab in the programming exercises, 663
CVIPlab prototype program, 4
CVIPlab�m, 638
CVIPlab�m file modifications, 648f
CVIPlab�mscript, 638
CVIPtools after creating the circle image, 102f
CVIPtools C libraries, 656f
CVIPtools compression window, 38f
CVIPtools development utility main windows, 43f
CVIPtools enhancement window, 37f
CVIPtools geometric restoration window, 534f, 537f
CVIPtools GUI main window, 32–33
CVIPtools help window, 41f
CVIPtools histogram slide/stretch/shrink, 410f
CVIPtools image viewer keyboard, 34t
CVIPtools main window, 33, 101f
CVIPtools restoration window, 37f
CVIPtools software, 4
CVIPtools utilities, 39
Cyan, 54
Cylindrical coordinate transform (CCT), 51, 52f, 631
D
Dark current, 24
Data compaction, 572
Data preprocessing, 323–326
Data visualization, 56864 Index
Decimation filter, 93f
Decision tree, 109f
Decomposition level, 274
Decompressor, 568, 569f
Deconvolution, 510
Degradation function, 509, 512–514
estimation of, 512–514
frequency domain, 510–512
spatial domain, 509–510
Degradation process model, 471
Delta length, 161
Depth maps, 29
Depth of field, 21
Detail/edge information, 433f
Detection, 145
Detection of anterior cruciate ligament rupture in
Canines, 711
introduction and overview, 711
materials and methods, 711
data normalization and pattern classification, 714
feature selection and extraction, 713–714
image database, 712
image preprocessing, 712–713
results and discussion, 714–716
Detection of Canine bone cancer, 717
material and methods, 718
color normalization, 719
data normalization and pattern classification, 720
digital infrared thermal imaging system, 718
experimental animals, 718
experimental methods, 720
feature selection and extraction, 719–720
mask creation, 719
software tools used, 719
thermographic images, 718–719
results and discussion, 720–721
Development tools, 40
DFT spectrum with various remap methods, 246f
Diagonal masks, 193
Differential coding, 570
Differential predictive coding (DPC), 596–603, 598f–599f
quantization comparison, 601f
with Lloyd–Max quantization, 602f–603f
Differential pulse code modulation (DPCM), 596
Digital cameras, 13
Digital image analysis, 69
arithmetic and logic operations, 76–80
basic binary object features, 97–100
basic image thresholding, 93–95
binary image analysis, 93–109
binary object classification, 101–109
connectivity and labeling, 95–97
image quantization, 86–93
preprocessing, 71–93
region of interest (ROI) image geometry, 71–76
spatial filters, 80–85
system model, 69–70
Digital image analysis and computer vision projects,
669–670
Digital image file formats, 55–57
Digital image processing, 3, 4f
Digital image processing and human vision projects, 671
Digital image processing system hardware, 14f
Digital image processing systems, 13
Digital image processing, overview, 384–391
Digital images, 17
Digital negative, 398
mapping equation, 398f
modified by inverse mapping equation, 398f
negative of image, 398f
original image, 398f
Digital subscriber lines (DSL) connections, 566
Digital television (DTV), 14
Digitization, 13
Digitizing (sampling), 15f
Dilation, 183–184, 187f
with iterative MOD method, 201–202
Direct Fourier reconstruction, 543
Directional difference filters, 435, 436f, 437f
Discrete cosine transform (DCT), 248–251, 606
Discrete cosine transform basis images, 251f
Discrete Fourier transform (DFT), 233
Discrete Haar transform, 255–257
Discrete transforms, 225–230, 226f
Discrete Walsh–Hadamardtransform, 252–255
Discrete wavelet transform, 272–277
Discriminant functions, 329
Domains, 606
DPC predictor, 600f
Dynamic window range, 584
Dynamic window range RLC, 589f–590f
Dynamically linked library (dll), 32
E
Eccentricity, see Aspect ratio
Edge detection
errors in, 145f
examples, 151f
examples with direction images, 152f–153f
with noise, 155f
Edge detection methods, 122, 200–201, 203f
Edge detection thresholding via histogram, 177f
Edge detector performance, 144–154
Edge detector-based sharpening algorithms, 439
Edge detectors, 432
Edge model, 126
Edge/line detection, 122–165
advanced edge detectors, 128–139
compass masks, 128
corner detection, 162–165
edge detector performance, 144–154
edges in color images, 139–144
gradient operators, 124–128
Hough transform, 154–162
Edge/line detection group, 632
Edge-preservingsmoothing filter, 446
Edges and lines, 122f
Edges in color images, 139–144
Editing CVIPlab�h, 662fIndex 865
Eight masks, 193
Ektachrome, 306
Electromagnetic (EM) spectrum, 17, 18f, 361
gamma waves, 17
infrared, 17
microwaves, 17
radio waves, 17
ultraviolet, 17
visible light, 17
x-rays, 17
Electron beams, 17
Electron imaging, 28
Electron microscopes, 28
Elongation, see Aspect ratio
Emboss filters, 85; see also Directional difference filters
EM radiation
alternating (sinusoidal) electric, 17
magnetic fields, 18
Encapsulated postscript (EPS), 56
Energy, 303
Energy compaction, 606
Enhancement filters, 82, 86f
Enhancement window, 35
histogram/contrast, 35
pseudocolor, 35
sharpening, 35
smoothing, 35
Entropy, 303, 572, 574f
Entry level parameter, 168
Erosion, 183–185, 185f
appendage removal, 200
with iterative MOD method, 199
Estimation of noise, 479–482
Euclidean distance, 146, 318
Euler number, 100f
Exponential adaptive contrast filter (Exp-ACE), 422f
F
Faint line defect detection in microdisplay (CCD)
elements, 766
design methodology, 767
line-detection algorithm, 767
analysis of the hough space, 771–772
edge detection, 769–771
preprocessing, 767–769
results and discussion, 772–773
False contouring, 372f
False contouring effect, 87, 88f
Fast algorithm filter, 445
Feature analysis, 295f, 317
data preprocessing, 323–326
distance and similarity measures, 318–322
feature vectors and feature spaces, 317–318
Feature extraction, 4, 296
color features, 305–306
feature extraction with CVIPtools, 313–316
histogram features, 300–305
region-based features, 313
shape features, 296–300
spectral features, 306–308
texture features, 308–313
Feature extraction with CVIPtools, 313–316, 317t
Feature file data, 109t
Feature selection window, 698
Feature spaces, 317–318
Feature tab, 107f–108f
Feature vectors, 317–318
Field of view (FOV), 21, 22f
Filtering, 259
band-pass filters, 267–271
band-reject filters, 267–271
high-pass filters, 264–266
low-pass filters, 259–264
Filtering with a sliding window, 418f
FireWire (IEEE 1394), 16
Flicker sensitivity, 371
F-number, 21
Four masks, 193
Fourier descriptors (FDs), 300
Fourier magnitude data, direct mapping of, 245f
Fourier spectra
of noise images, 480f
of real images, 480f
to reduce Gaussian noise effects, 492f–493f
Fourier spectrum, 276f
Fourier spectrum power, 308
Fourier transform, 230–248
decomposing a square wave, 231f
discretefourier spectrum, 243–248
example, 232f
fourier transform properties, 239–242
one-dimensional discrete fourier transform, 233–236
two-dimensional discrete fourier transform, 237–239
Fourier transform phase, 238f
Fourier transform properties, 239–242
convolution, 240
linearity, 239
modulation, 240, 242f
periodicity, 241–242
rotation, 240, 243f
sampling and aliasing, 242–243
translation, 240
Fourier-slice theorem, 543, 543F
Fovea, 364
Fractal compression, 604f
Frame grabber, 13
FreeBSD, 32
Frei–Chen masks, 134, 138f
Frei–Chen masks for corner detector, 165f
Frei–Chen projection, 139f
Frei–Chen results using CVIPtools, 140f
Frequency domain filtering, 514f
Frequency domain filters, 514
adaptive filtering, 523
band-pass filters, 523–526
band-reject filters, 523–526
constrained least squares filter, 520–521
geometric mean filters, 521–522
inverse filter, 515–517866 Index
Frequency domain filters (Continued)
notch filters, 523–526
practical considerations, 526–528
Wiener filter, 518–520
Frequency domain low-pass filtering, 443
Frequency domain pseudocolor, 427f
Frequency-modulated (FM) beat signals, 30
F-stop, 21
Fundus images application development example, 683f
Fuzzy c-means, 172
Fuzzy features, 320
G
Gabor filters, 312
Gabor filters for pathology classification in veterinary
thermograms, 807
background, 808
feature extraction, 808–809
gabor filter, 808
results and discussion, 809
ACL, 811–812
bone cancer: elbow/knee—anterior, 810–811
bone cancer: elbow/knee—lateral, 811
bone cancer: wrist-lateral, 811
feline hyperthyroid, 811
Gamma-correctionequation, 404
Gaussian/uniform/salt-and-pepper noise distribution,
474f–476f
Generalized Hough transform, 181
Generic imaging sensors
linear/line sensor, 23f
single imaging sensor, 23f
two dimensional/array sensor, 23f
Geometric distortion, 529f
Geometric distortion correction
distorted image, 9f
restored image, 9f
Geometric mean (GM) filter, 494, 495f, 521–522
Geometric restoration procedure, 532–534, 533f, 535f–536f
Geometric restoration with CVIPtools, 534–537
Geometric shapes images, 247f–248f
Geometric transforms, 528, 528f
geometric restoration procedure, 532–534
geometric restoration with CVIPtools, 534–537
gray-level interpolation, 531–532
spatial transforms, 528–531
Gigabit Ethernet (IEEE 802�3), 16
GIST features, 313
Gradient masks, 138f
Gradient operators, 124–128
Gradient vector flow snake (GVF snake), 181, 182f
Graphical user interface (GUI), 32
Graphics interchange format (GIF), 55; see also Image file
formats
Gray code, 580f
Gray-level compression, 395
Gray level co-occurrence matrices, 311f
Gray level co-occurrence matrix methods, 310
Gray level dependency matrix methods, 310
Gray-level histogram, 404
Gray-level interpolation, 531–532, 531f
Gray-level mapping II in CVIPtools, 425f
Gray-level morphological filtering, 204f
Gray-level reduction, 86
Gray-level run-length coding, 583–585
Gray-level scaling, 395; see also Gray-scale modification
Gray-level stretching, 395–396
Gray-level stretching with clipping, 397
mapping equation, 397f
modified image, 397f
original image, 397f
Gray-level transformation, 395; see also Gray-scale
modification
Gray-level variance, 167
Gray scale images, 46–47, 47t
Gray-scale modification, 395, 396f
Gray-scale modification with CVIPtools, 400f
Green cones, 362
H
Haar transform, 256f
Halftoning and dithering, 90, 91f
Hamming filter, 538
Harmonic mean filter, 495, 496f
Harris corner detector, 164f
CRF(r,c) result, 164
final detected corners, 164f
horizontal and vertical gradient, Gaussian, 164f
horizontal lines strength, 164f
original image, 164f
vertical lines strength, 164f
Harris method, 162
HDTV screen resolution, 369–370
Help button, 35
Help window, 40
Hexagonal grid, 198f
Hierarchical image pyramid, 16, 17f
High-boost spatial filtering, 434f
High-definition television (HDTV), 15f, 369
High-frequency emphasis (HFE) filtering, 266f, 269f, 432–435
High-pass filtering, 432
High-pass filters, 264–266, 267f–268f, 269f
Histogram equalization, 408–411, 411f, 413f–414f, 417f
Histogram equalization of color images, 428f
Histogram features, 300–305, 301f–302f, 304f–305f
Histogram modification, 404–415, 405f
Histogram peak finding, 172f
Histograms, 95f
Histogram scaling, 404
Histogram shrinking, 408
histogram of image, 408f
image after shrinking, 408f
original image, 408f
Histogram slide technique, 408, 410f
Histogram specification, 409, 411–412, 415f–416f
Histogram stretching, 406
after histogram stretch, 406f
histogram of image after stretch, 406fIndex 867
histogram of image, 406f
image, 406f
low-contrast image, 406f
tight cluster, 406f
Histogram stretching with clipping, 407
histogram of image, 407f
histogram of original image, 407f
image after histogram stretching with clipping, 407f
image after histogram stretching without clipping, 407f
original image, 407f
Histogram thresholding segmentation, 172, 173f
Hollyhock pollen, 29f
Homomorphic filtering process, 435–438, 437f, 438f
filtering, 436
fourier transform, 436
inversefourier transform, 436
inverse log function, 436
natural log transform (base e), 436
Horizontal synch pulse, 13
Hough transform, 154–162, 157f
CVIPtools parameters, 161–162
flowchart, 158f
postprocessing algorithm details, 160f
quantization block size, effects, 159f
to find airport runway, 161f
Hue/saturation/lightness (HSL), 48, 49f, 428
Hue/saturation/value (HSV), 428
Hue–saturation–lightness (HSL), 631
Hue–saturation–value (HSV), 631
Huffman coding example, 576f–577f, 579f
Huffman coding, 575–577
Human eye, 361f
blind spot, 362
cones, 361f
energy receptors, 361
Fovea, 364
image sensors, 361f
iris, 362
lateral inhibition, 365
lens, 361
neural system model, 365f
photoreceptors, 361
pupil, 361
retina, 361
RGB values, 363
rods, 361f
tristimulus (three stimuli) curves, 362, 362f
Human visual perception, 359
brightness adaptation, 370–371
human visual system, 360–365
perception and illusion, 373–378
spatial frequency resolution, 365–370
temporal resolution, 371–373
Human visual system, 3, 360
brain, 360
eye, 360
Hybrid and Wavelet methods, 610–616
Hybrid median filter, 485
Hybrid median filtering, 486f
Hyperplane, 330
Hyperquadrics, 330
Hysteresis thresholding, 133
I
Ideal and real edge, comparison, 125f
Ideal low-pass filter, 261f
Image addition examples, 78f
Image after thresholding, 106f
Image analysis, 3, 4–6
Image analysis and computer vision, 4–6
Image analysis details of data reduction, 70f
Image analysis domains, 69
Image analysis process, 69
data reduction, 69
feature analysis, 69
preprocessing, 69
Image comparison interface, 682f
Image compression, 9, 565
image file compressed to 1/100, 10f
image file compressed to 1/200, 10f
image file compressed to 1/50, 10f
original image, 10f
Image corrupted by periodic noise, 481f
Image data and file structures, 664–669, 665f
Image division, 80f
Image enhancement, 9
gray-scale modification, 395
adaptive contrast enhancement, 415–422
color, 423–431
histogram modification, 404–415
mapping equations, 395–404
image sharpening, 432
directional difference filters, 435
edge detector-based sharpening algorithms, 439
high-frequency emphasis, 432–435
high-pass filtering, 432
homomorphic filtering, 435–438
unsharp masking, 438
image smoothing, 442
convolution mask low-pass filtering, 443
frequency domain low-pass filtering, 443
nonlinear filtering, 443–452
Image enhancement examples, 394f
Image enhancement process, 393f, 394f
Image enhancement techniques
global operations, 393
mask operations, 393
point operations, 393
Image enlargement, 72
Image fidelity criteria, 379, 386–387
objective fidelity measures, 379–381, 386–387
subjective fidelity measures, 381–383, 387
Image file formats, 55
Image file header, 55
Image formation and sensing, 17
acoustic imaging, 26–27
computer-generated images, 30–31
electron imaging, 28
imaging outside the visible range, 24–26868 Index
Image formation and sensing (Continued)
laser imaging, 28–30
visible light imaging, 18–24
Image masking, 80
Image morphing, 78
Image multiplication, 81f
Image objects, 124
image of objects in kitchen corner, 124f
morphological filtering, 183–204
Image processing, 11
Image processing and human vision, 7–11
Image processing systems
hardware, 13
software, 13
Image quantization, 76, 86–93
Image queue, 32
Image reconstruction, 538
fourier-slice theorem and direct fourier
reconstruction, 543
radon transform, 538–542
reconstruction using backprojections, 538
Image representation, 45
binary images, 45–46
color images, 47–54
digital image file formats, 55–57
grayscale images, 46–47
multispectral images, 54
Image restoration, 7
image with distortion, 8f
process, 471, 472f
restored image, 8f
Image rotation, 77f
Image segmentation categories, 4, 121f, 165
Image sensors, 361
Image sharpening
original image, 10f
sharpened image, 10f
Image smoothing, 442–452
arithmetic mean, 445f, 446f
Gaussian, 446f
original image, 445f
with median filter, 447f–448f
Image subtraction, 79f
Image transforms, 4
Image translation, 77f
Image viewer, 34–35
Impairment tests, 381
Improved grayscale (IGS) quantization method, 87, 89f
Improved MMSE filter flowchart, 500f–501f
Impulse noise, 475
Incoherent light, 29
Individual bit-planes in a color image, 373f–374f
Inertia, 310
Information, 567
Information theoretic definition, 572
Information theory, 591
Infrared (IR) images, 24
near infrared band, 26f
showing water vapour, 26f
thermographic images, 26
Infrared imaging, 5
Input_image�m, 639
Intensity level slicing, 400
Intensity-level slicing, 397, 399
desired gray level range, 399f
intensity (brightness) levels, 399f
original image, 399f
returns the original gray levels, 399f
Intensity slicing, 424
Interband redundancy, 568
Interframe redundancy, 568
Interlaced video, 13
Intermediate image after processing, 7f
International standards organization (ISO), 607
International telecommunications union-radio (ITU-R), 581
Interpixel redundancy, 568
Invariant moment features, 299t
Inverse cosine transform, 250
Inverse difference, 310
Inverse filter and Wiener filter, comparison, 519f–520f
Inverse filter, 515–517, 517f
Inverted LoG, 130f
Invoking CVIP-ATAT, 674f, 690f
Irradiance, 19, 20f
Iterated median filtering, 485f
Iterative morphological filtering, surrounds, 198f
ITU-R 601, 53
J
Joint photographers expert group (JPEG), 55, 250, 607
JPEG2000, 55
JPEG2000 algorithm, 613
JPEG2000 compared to standard JPEG, 615f–616f
K
Kernel functions, 330
Kirsch compass masks, 128
Kirsch direction, 153f
Kirsch magnitude, 153f
Kirsch operator, 151f
K-means, 593
K-means clustering algorithm, 94
K-nearest neighbor method, 328
Kodachrome, 306
Kuwahara filter, 446, 448f–449f
L
Labelingalgorithm flowchart, 97f
Land types, 753
data reduction and feature extraction, 754–755
introduction and overview, 753–754
object classification, 756–758
Laplacian masks, 127, 138f
Laplacian of a Gaussian (LoG), 129
Laplacian operators, 127, 151f
Laplacian-type filters, 85
Laser imaging, 28–30Index 869
Lasers, 17
Lateral inhibition, 373
Laws texture energy masks, 311
Leave-one-out testing in combinatoricmode, 697f
Lempel–Ziv–Welch Coding, 581–582
Lempel–Ziv–Welch (LZW) coding algorithm, 55, 581
Light amplification by stimulated emission of radiation
(LASER), 28
Lighting and object effects, 94f
Limit parameter, 96f
Line angles, 161
Line masks, 138f
Line pixels (min), 161
Linear discriminant, 330f
Linear filter, 82
Linear interpolation technique, 73
Linux, 32
Lloyd–Max quantizer, 600f
Local enhancement, 415
Localization, 145
Lock input, 32
Logarithmic adaptive contrast filter (Log-ACE), 421f
Logic operations, 76–80
AND, 76
NOT, 76
OR, 76
Look-up-table (LUT), 55, 56f
Lossless compression methods, 572
arithmetic coding, 582–583
Huffman coding, 575–577
Lempel–Ziv–Welch coding, 581–582
run-length coding, 578–581
Lossless methods, 38, 567
Lossy, 38
Lossy bitplane-run length coding, 586f–587f
Lossy compression methods, 583
block truncation coding, 585–589
differential predictive coding, 596–603
gray-level run-length coding, 583–585
hybrid and wavelet methods, 610–616
model-based and fractal compression, 603–606
transform coding, 606–610
vector quantization, 589–596
Lossyimage compression, 584f
Low-pass butterworth filters, 263f–266f
Low-pass filters, 259–264
Lumber counting and grading, 7f
M
Macbeth color chart, 306
Mach band effect, 373, 376f
Magnetic resonance imaging (MRI), 24, 538
Magnitude image information, 238f
Mapping equations, 395–404
Marr–Hildreth algorithm, 129
Matlab CVIP toolbox, 32, 631
CVIP toolbox function categories, 631
arithmetic and logic, 631
band, 631
color, 631–632
conversion of image files, 632
display, 632
edge/line detection, 632
geometry, 632
histogram, 632
mapping, 633
morphological, 633
noise, 633
objective fidelity metrics, 633
pattern classification, 633
segmentation, 634
spatial filters, 634
transform, 634
transform filters, 634
help files, 634–636
M-files, 636
Matlabhelp, 635f–636f
Matrices and pointers, 666f
Matrix, 45
Max video frequency, 368–369
Maximum filter, 486, 487f–488f
Mean, 302
Mean filters, 82, 483, 489–497
Median filter, 82–83, 84f, 484, 484f
Median segmentation algorithms, 172
Medical imaging, 78
Melanoma and seborrheic keratosis differentiation, 774
materials and methods, 775–776
texture analysis experiments, 776–781
Memory aid, 235f
Merge parameter, 168
Metameric colors, 363–364
Metamers, 363
Mexican hat operator, 129, 130f
Microchip, logic gate, 29f
Microdisplay chips, 5, 6f
Microsoft windows bitmap (BMP) format, 55
Midpoint filter, 487
Minimizing within group variance, 176
Minimum filter, 486, 487f–488f
Minimum mean-square error estimator (MMSE), 518
Minimum mean-squared error (MMSE) filter, 498, 499f
Mode, 303
Model-based and fractal compression, 603–606
Modeling the PSF for motion Blur, 510f
Modulation transfer function (MTF), 511
Modulation/optical transfer function, 511–512
Monochrome (“one color”) images, 46, 47t
Monochrome video standards
RS-170A, 13
RS-330, 13
RS-343A, 13
Moore–Penrose generalized inverse matrix, 432
Moravec detector, 162, 163f
Morphological filtering, 183–204
Mosquito, SEM image, 29f
Mouse commands, 34t
Multilevel block truncation coding (BTC), 594f
Multiresolution algorithms, 166870 Index
Multiresolution decomposition, 274
Multispectral and radio wave images, 27
GOES, 27f
MRI images, 27f
Multispectral geostationary operational environmental
satellite (GOES), 27
Multispectral images, 24, 54
N
Nearest centroid, 328
Nearest neighbor method, 328
Negative image, creating, 199
Negative predictive value (NPV), 334
Neural network, 332f
Neural processing system model, 365f
New algorithm resulting images, 685f–686f
Noise, 69
Noise histograms, 473–478
Noise in images, 123f
Noise models, 472–482
estimation of noise, 479–482
noise histograms, 473–478
periodic noise, 478–479
Noise pattern, 527f
Noise removal
noise removed, 8f
noisy image, 8f
Noise removal using spatial filters, 483–508
adaptive filters, 497–508
mean filters, 489–497
order filters, 483–489
Noise with crop and histogram, estimating, 482f
Nonideal low-pass filters, 262f
Noninterlaced video, 13
Nonlinear filter, 84
Nonlinear filtering, 443–452
Nonmaximasuppression, 133f
Nonuniform quantization, 571, 606
Notch filters, 270f, 523–526, 524f
NTSC, 13
Nyquist rate, 242
O
Objective fidelity criteria, 379
Objective fidelity measures
peak signal-to-noise ratio, 380f
root-mean-square error, 381f
OFFSET value, 408
One-dimensional discrete fourier transform, 233–236
1D Walsh–Hadamard basis functions, 252f
Opening CVIPlab_Project�sln, 657f
Opening operation, 185, 185f, 189f
Optic nerve, 360
Optical illusions, 375, 378f
Optical image, 45
Optical transfer function (OTF), 511
OR’ing two circles, 103f
Order filters, 483–489
Order statistics, 483
Original DCT-based JPEG, 611f–612f
Original JPEG DCT coefficient quantization tables, 610f
Orthogonal image, 230
Orthonormal image, 230
Otsu method, 176
Outlier removal, 323
Output from CVIPtoolsanalysis, 336f
P
PAL, 13
Parametric anisotropic diffusion (AD) filter, 508f
Parametric Wiener filter, 521
Passband, 60
Pattern classification, 4, 295f, 326
algorithm development, 327
classification algorithms and methods, 328–332
cost/risk functions and success measures, 332–335
pattern classification with CVIPtools, 336
Pattern classification with CVIPtools, 336
PBM (binary), 55; see also PPM formats
PCT/median color segmentation algorithm, 174
PCT/median segmentation algorithm, 177f
Peak signal-to-noise ratio, 380, 382f
Perception and illusion, 373–378
Perimeter, 297f
Periodic noise, 478–479
Periodicity and discrete Fourier transform symmetry, 244f
Persistence, 371
PGM (grayscale), 55; see also PPM formats
Phase contrast filtering, 432
Photon noise, 24
Photons, 17
Photopic(day-light) vision, 362
Piece-wise linear modification with CVIPtools, 401, 403f
CVIPtools screen shot, 401f–402f
mapping equation, 401f
Pixel-by-pixel processing, 523
Pixels, 16, 96
Plate of spaghetti, 131
PNM, 55; see also PPM formats
Point spread function (PSF), 509–511
Points in the world and in image, 20f
Portable document format (PDF), 56
Portable network graphics (PNG), 56
Positron emission tomography (PET), 538
Power, 306
Power spectrum equalization filter, 521
power-law equation, 404
power-law transform, 404
PPM (color), 55; see also PPM formats
PPM formats, 55
Practical Wiener, 519
Pratt’s figure of merit (FOM), 145–146, 148f–150f
Preprocessing, 38, 71, 71f
Prewitt direction, 152f
Prewitt magnitude, 152f
Prewitt operator, 151f
Principal component analysis (PCA), 259Index 871
Principal component transform (PCT), 54, 172, 176f, 225,
257–259, 258f, 326, 631
Probability density function (PDF), 473
Probe, 185
Programming exercises, 390
brightness adaptation, 390
optical illusions, 390
spatial resolution, 390
Project interface, 676f
Project topics, example, 670
Projections, 100f
Projection-slice theorem, see Fourier-slice theorem
Pruning, 196–197
Pseudocolor, 423
Pseudocolor in frequency domain, 426
block diagram of the process, 426f
fourier filters, 426f
Pseudocolor in spatial domain, 423f
Pseudocolor techniques, 427
Pseudomedian filter, 445
Psychovisual redundancy, 568
Pulses, 30
Pupil, 370
Q
Quadtreedata structure, 167f
Quality tests, 381
Quantized hough space, 158f
Quantizing with a codebook, 595f
Quantum efficiency, 24
R
Radiance, 19, 20f
Radon transform, 538–543, 542f
Range compression, 404
Raster images, see Bitmap images
Rayleigh, negative exponential and gamma noise
distributions, 477f–478f
Reconstruction using backprojections, 538
Recursive region splitting, 172
Red cones, 362
Reflectance function, 18
color image, 19f
monochrome image, 19f
Reflected ultraviolet imaging systems, 5
Region growing and shrinking methods, 165–168
Region of interest (ROI) image geometry, 71–76
Regular and irregular mapping, 535f
Remapping for display, 57f
Rendering, 55
Reset button, 35
Restoration window, 36–38
frequency filter, 38
geometric transforms, 38
noise, 36
spatial filter, 38
Result file, 696f
Results from changing Gaussian variance, 135f–136f
Results from changing high threshold, 134f
RGB calculations using tristimulus curves, 363
Ripple masks, 138f
Roberts operator, 125, 151f
Robinson compass masks, 128
Robinson direction, 153f
Robinson magnitude, 153f
Robinson operator, 151f
Rods, 361f, 362f
Root-mean-square error, 379
Root-mean-square signal-to-noise ratio, 379
RST-invariant features, 299f
with noise, 300f
R-table, 181
Rubber-sheet transforms, 528
Run-length coding, 578–581
Running CVIPlab in Matlab, 644f
S
Salt and pepper noise to blurred composite image, 105f
Save compressed data, 38
Scalar quantization, 591
Scale-invariant feature transform (SIFT), 313
Scanning electron microscope (SEM), 28, 29f
Scatterplot, 330
Scotopic(night) vision, 362
SCT/Centercolor segmentation algorithm, 172, 174f
applied to skin lesion image, 175f
SDTV screen resolution, 368–369
SECAM, 13
Second-order histogram methods, 310
Seed regions, 167
Segmentation, 165
boundary detection, 176–182
butterfly after edge detection, 124f
butterfly image, 124f
clustering techniques, 168–176
combined segmentation approaches, 182–183
image after edge detection, 124f
region growing and shrinking methods, 165–168
Segment length (min), 161
Sensitivity, 333
Sensor equation, 23
Sensors, 17
Separability, 239
Sequency, 252
Sequential method, 203f
Settings for header files, 661f
Shannon’s rate distortion theory, 591
Shape features, 296–300, 297f
Sharpening algorithm I, 439, 441f
Sharpening algorithm II, 439, 442f
Shen–Castan algorithm, 133, 137f
Shepp–Logan filter, 538
Shot noise, 475
Silicon Graphics, Inc (SGI), 56
Simple decision tree, 108
Simultaneous contrast, 374, 377f
Single photon emission computed tomography (SPECT), 538872 Index
Single response, 145
Sinusoidal waves, 234f
Skeletonization, 192
after 10 iterations, 203f
after 5 iterations, 203f
original image, 203f
results with eight masks, 203f
results with four masks, 203f
with irregular shapes, 194f
with simple shapes, 193f
Skew, 303
Skin lesion classification, 734
experiments and data analysis, 738
lesion feature space, 738–741
object feature space, 741–742
introduction and project overview, 734–735
materials and methods, 735
creation of relative color images, 735
feature extraction, 736
image database, 735
lesion and object feature spaces, 737
segmentation and morphological filtering, 736
statistical models, 737–738
Smoothing filters comparison, 452f
Smoothing with convolution filters, 444f
Snake eating edge linking algorithm, 178
Sobel direction image, 152f
Sobel magnitude image, 152f
Sobel operator, 125, 151f
Softmax scaling, 326
Spatial domain processing methods, 393
Spatial filters, 80–85
Spatial frequency, 227f
Spatial frequency resolution, 365–370
cycles per degree, 367f
higher frequency, 366f
low frequency, 366f
one-dimensional square wave, 366f
physical mechanisms, 367
Spatial reduction, 86, 92f
Spatial transforms, 528–531, 529f
Specificity, 333
Spectral aliasing, 244f
Spectral bands, 361
Spectral features, 306–308, 307f
Spectral region power, 06
Speeded up robust features (SURF), 313
Spherical coordinate transform (SCT), 51, 52f, 172, 631
Spike noise, 475
Split and merge technique, 166
local mean vs global mean, 168
local standard deviation vs global mean, 168
pure uniformity, 168
segmentation, 169f
texture, 168
variance, 168
weighted gray-level distance, 168
Spur removal, 196f
Standard anisotropic diffusion (AD) Filter, 503, 505f–507f
Standard deviation, 303
Standard normal density (SND), 633
Standard ultrasound image, 28f
Standard-definition television (SDTV), 15f
Stopband, 60
Strawberry, 29f
Structuring element (SE), 183
Subimage-by-subimageprocessing, 523
Subjective fidelity criteria, 379
Subjective fidelity scoring scales, 383t
Subsampling, 92
Sun Raster format, 56
Sun Solaris, 32
Supervised training, 327
Supplementary programming exercises, 391
neural processing system model, 391
objective fidelity measures, 391
subjective fidelity measures, 391
Support vector machines (SVMs), 330
Support vectors, 330
SVM Kernel function, 331f
SVM optimal hyperplane, 331f
System model, 69–70, 471–472
System output, 7f
T
Tagged image file format (TIFF), 55; see also Image file
formats
Tanimoto metric, 319
Temporal resolution, 371––372, 375
Test interface, 680f
Texture features, 308–313, 309f
Thermographic imaging, 24
Thermography-based prescreening software tool, 814
clinical application development, 815
algorithm database, 815
graphical user interface (GUI), 815–817
image database, 815
process flow, 815
results and discussion, 817
Thinning operation, 191
Thinning the top horizontal line, 191–192
3D ultrasound image, 28f
Threshold coding, 607
Threshold�m, 640
Threshold parameter, 168
Threshold_Setupfunction, 651
Thresholdingnoisy images, 180f
Tiepoints, 529
Tomogram, 538
Toolbox libraries, 655
Toolkit libraries, 655
Training set size, 328f
Training set, 109
Transform coding, 606–610
Transform coefficients, 228f
Transform/VQ compression, 614f
Transmission electron microscope (TEM), 28
Tristimulus curves, 362
Two images selection, XOR, 104fIndex 873
Two-dimensional discrete fourier transform, 237–239
Two-dimensional feature space, 318f
Two-dimensional sinusoid, 237f
Two-stage run of CVIP-ATAT, 680f
Typical Blur mask coefficients, 512
U
Ultrahigh definition (UHD), 16
Unequal (or variable) length code, 575
Uniform bin-width quantization, 90, 91f
Uniform quantization, 571
Universal serial bus (USB), 16
Unsharp masking, 438, 440f
Unsharp masking algorithm, 438
Unsharpmasking enhancement flowchart, 439f
Unsupervised training, 327
UPDATE block, 97
Utilities functions, 101, 101f
Utilities window, 40
UV imaging, 24
V
Variable bin-width quantization, 91f–92f
Variable bit rate, 572, 606
Vector, 45
Vector images, 55
Vector inner product, 134, 254
Vector inner product/projection, 230f
Vector outer product, 253, 254f
Vector quantization (VQ), 589–596, 596f–597f
Vectorization, 642–643
Vertical synch pulse, 13
Video signals, 13, 14f
analog video signal, 14f
one frame, two fields, 14f
View labeled image button, 315
Vignetting effect, 22f
VIPM file format, 650t
Visible light imaging, 18–24, 19f
Visible light spectrum, 360f
Vision, 360
Visual information, 3
Visualization in image processing (VIP) format,
56, 632
Vole detection application with CVIPtools and
OpenCV, 801
camera sensor, 804–806
common vole detection, 802
vole detection algorithm, 802–804
W
Walsh–Hadamard basis images, 254f–255f
Walsh–Hadamard spectrum, 276f
Walsh–Hadamard transform (WHT), 252, 252f
Watershed-based approach to skin lesion border
segmentation, 760
experiments, results and conclusions, 765–766
materials and methods, 760
B-spline border smoothing, 763–764
error estimating, 765
noise removal, 763
object histogram merging, 763
preprocessing, 760
watershed algorithm, 761–762
Watershed lines, 168
Watershed segmentation algorithm, 168, 170f–171f
Wavelet transform
1-level decomposition, 275f
2-level decomposition, 275f
display, 275f
three-level decomposition, 275f
Wavelet/VQ compression, 613f
White noise, 477
Wiener filter, 518–520
Wiener filter response, 518f
Write_Imagefunction, 668
X
Xform/vector quantization(XVQ), 611
Xform/vector quantization compression algorithm
parameters, 612t
X-ray and UV Image
chest X-ray, 25f
dental x-ray, 25f
fluorescence microscopy images of cells, 25f
one “slice” of computerized tomography (CT), 25f
Y Yp
mean filter, 497f
Z
Zero-frequency coefficient, 608
Zonal coding, 607, 608f
Zonal compression with DCT and Walsh transforms, 609f
Zonal mask, 607
Zoom process, 72
Zooming methods, 73f
كلمة سر فك الضغط : books-world.net
The Unzip Password : books-world.net
أتمنى أن تستفيدوا من محتوى الموضوع وأن ينال إعجابكم
رابط من موقع عالم الكتب لتنزيل كتاب Digital Image Processing and Analysis Applications with MATLAB and CVIPtools
رابط مباشر لتنزيل كتاب Digital Image Processing and Analysis Applications with MATLAB and CVIPtools 
|
|
