Image Processing: Principles and Applications

Preface.

1. Introduction.

1.1 Fundamentals of Image Processing.

1.2 Applications of Image Processing.

1.2.1 Automatic visual inspection system.

1.2.2 Remotely sensed scene interpretation.

1.2.3 Biomedical Imaging Techniques.

1.2.4 Defence surveillance.

1.2.5 Moving Object tracking.

1.3 Human Visual Perception.

1.3.1 Eyes detect motion.

1.3.2 Structure of Eyes.

1.3.3 Nervous Aspects of the Visual Sense.

1.3.4 Intuitionistic Philosophy.

1.3.5 Gray and Color Perception.

1.4 Components of an Image Processing System.

1.4.1 Digital Camera.

1.4.2 Capturing Colors.

1.5 Organization of this book.

1.6 How is this book different ? 16.

1.7 Summary 17.

References 17.

2. Image Formation and Representation.

2.1 Introduction.

2.2 Image formation.

2.2.1 Illumination.

2.2.2 Reflectance Models.

2.3 Sampling and Quantization.

2.3.1 Image Quantization.

2.4 Binary Image.

2.4.1 Geometric properties.

2.5 Connected component labeling.

2.5.1 Three Dimensional imaging.

2.5.2 Stereo images.

2.5.3 Point Spread Function.

2.6 Image fled formats.

2.7 Some Important Notes.

2.8 Types of Image Processing Operations.

2.9 Summary.

References.

3. Color and Color Imagery.

3.1 Introduction.

3.2 Perception of Colors and Spectral sensitivity of human eyes.

3.3 Color Space Quantization and the Just Noticeable Difference.

(JND).

3.3.1 Need for color spaces.

3.4 Color Space and Transformation.

3.4.1 CMYK space.

3.4.2 NTSC or YIQ color space.

3.4.3 Y C_bC_r color space.

3.4.4 Perceptually uniform color space.

3.4.5 Need for perceptually uniform color space.

3.4.6 CIELAB color Space.

3.5 Color Interpolation or Demosaicing.

3.5.1 Non-adaptive color interpolation algorithms.

3.5.2 Adaptive algorithms.

3.5.3 A Fuzzy Assignment Based Adaptive Algorithm.

3.5.4 Experimental Results.

3.6 Summary.

References.

4. Image Transformation.

4.1 Introduction.

4.2 Fourier Transforms.

4.2.1 One-Dimensional Fourier Transform.

4.2.2 Two-Dimensional Fourier Transform.

4.2.3 Discrete Fourier Transforms (DFT).

4.2.4 Transformation Kernels.

4.2.5 Matrix Form Representation.

4.2.6 Properties.

4.2.7 Fast Fourier Transforms.

4.3 Discrete Cosine Transform.

4.4 Walsh Hadamard Transform (WHT).

4.5 Karhaunen-Loeve Transform or Principal Component Analysis.

4.5.1 Covariance Matrix.

4.5.2 Eigen vector and Eigen values.

4.5.3 Principal Component Analysis.

4.5.4 Singular Value Decomposition.

4.6 Summary.

References.

5. Discrete Wavelet Transform.

5.1 Introduction.

5.2 Wavelet Transforms.

5.2.1 Discrete Wavelet Transforms.

5.2.2 Concept of Multiresolution Analysis.

5.2.3 Implementation by Filters and the Pyramid Algorithm.

5.3 Extension to Two-Dimensional Signals.

5.4 Lifting Implementation of the DWT.

5.4.1 Finite Impulse Response Filter and Z-transform.

5.4.2 Euclidean Algorithm for Laurent Polynomials.

5.4.3 Perfect Reconstruction and Polyphase Representation of Filters.

5.4.4 Lifting.

5.4.5 Data Dependency Diagram for Lifting Computation.

5.5 Why Do We Care About Lifting?

5.6 Applications Areas in Image Processing.

5.7 Summary.

References.

6. Image Enhancement and Restoration.

6.1 Introduction.

6.2 Distinction between image enhancement and restoration.

6.3 Spatial Image Enhancement Techniques.

6.3.1 Unsharp Masking and Crisping.

6.3.2 Spatial Low Pass and High Pass Filtering.

6.3.3 Image Contrast Enhancement.

6.3.4 Local Area Histogram Equalization.

6.3.5 Histogram Hyperbolization.

6.3.6 Arithmatic/Logic operation for Enhancement.

6.4 Noise Filtering.

6.5 Image Enhancement - Frequency Domain approach.

6.5.1 Averaging and Spatial Low Pass Filtering.

6.5.2 Directional Smoothing.

6.5.3 Median Filtering.

6.5.4 Homomorphic Filter.

6.6 Noise Modeling.

6.6.1 Types of Noise in an Image and Their Characteristics.

6.7 Image Restoration.

6.7.1 Image Restoration of impulse noise embedded images.

6.7.2 Restoration of blurred image.

6.7.3 Inverse Filtering.

6.7.4 Wiener Filter.

6.7.5 Singular Value Decomposition.

6.8 Summary.

References.

7. Image Segmentation.

7.1 Preliminaries.

7.2 Edge, Line, and Point Detection.

7.3 Edge Detector.

7.3.1 Robert Operator Based Edge Detector.

7.3.2 Sobel Operator Based Edge Detector.

7.3.3 Prewitt Operator Based Edge Detector.

7.3.4 Kirsch operator.

7.3.5 Canny's Edge Detector.

7.3.6 Operators Based on Second Derivative.

7.4 Image Thresholding Techniques.

7.4.1 Problems encountered and possible solutions.

7.4.2 Entropy Based Thresholding.

7.4.3 Region Growing.

7.4.4 Clustering of Multiband images.

7.5 Color Image Segmentation.

7.6 Waterfall algorithm for segmentation.

7.7 Document Image segmentation.

7.7.1 Match-based segmentation.

7.8 Summary.

References.

8. Recognition of Image Patterns.

8.1 Introduction.

8.1.1 Decision Theoretic Pattern Classification.

8.2 Bayesian Decision Theory.

8.2.1 Parameter estimation.

8.2.2 Minimum Distance Classification.

8.3 Non-parametric Classification.

8.3.1 K-Nearest-Neighbor Classification.

8.4 Unsupervised Classification Strategies - clustering.

8.4.1 Single Linkage Clustering.

8.4.2 Complete Linkage clustering.

8.4.3 Average Linkage Clustering.

8.5 K-means Clustering Algorithm.

8.5.1 Syntactic Pattern Classification.

8.6 Primitive selection Strategies.

8.7 High Dimensional Pattern Grammars.

8.8 Formal Linguistic model.

8.9 Automata Theory.

8.9.1 Grammatical Inference.

8.10 Structural recognition of imprecise Patterns.

8.11 Symbolic Projection Method.

8.12 Classification using Neural Networks.

8.12.1 Error Backpropagation.

8.13 Crisp Neural Networks For Scene Classification.

8.14 Architecture of Back propagation network.

8.14.1 Kohonen's Self-Organizing Feature Map.

8.14.2 Counter propagation Neural Network.

8.15 Research Direction.

8.16 Summary.

References.

9. Texture and Shape Analysis.

9.1 Introduction.

9.1.1 Classification of textures.

9.1.2 Discriminatory Power of Co-occurrence matrix.

9.2 Drawbacks of Grey Level Co-occurrence Matrix (GLCM).

9.2.1 Tone and Texture.

9.2.2 Weak and Strong Textures.

9.2.3 Primitives.

9.3 Spatial Relationship.

9.4 Weak Texture Measures.

9.5 Strong Texture Measures and Generalized Co-occurrence.

9.6 Texture Spectrum.

9.7 Texture Classification using Fractals.

9.7.1 Fractal lines and shapes.

9.8 Fractals in Texture Classification.

9.8.1 Computing fractal Dimension using Covering Blanket method.

9.9 Structural Methods.

9.10 Shape Analysis.

9.10.1 Polygon as shape Descriptor.

9.11 Dominant points in Shape Description.

9.11.1 Freeman Chain Code.

9.11.2 Curvature and its role in shape determination.

9.12 Polygonal Approximation for Shape Analysis.

9.13 Automatic recognition of Guns.

9.13.1 The Polygonal Approximation.

9.14 Active Contour modeling.

9.15 Gestalt Theory of Perception.

9.16 Summary.

References.

10. Fuzzy Set Theory in Image Processing.

10.1 Introduction to Fuzzy Set Theory.

10.2 Why Fuzzy Image?

10.3 Introduction to Fuzzy Set Theory.

10.4 Preliminaries and Background.

10.4.1 Fuzzication.

10.4.2 Basic Terms and Operations.

10.5 Image as a Fuzzy Set.

10.5.1 Selection of the Membership Function.

10.6 Fuzzy Methods of Contrast Enhancement.

10.6.1 Contrast Enhancement Using Fuzzifier[7, 8].

10.6.2 Asymmetry S function [3].

10.7 Determination of the Fuzzication Parameters.

10.8 Results.

10.9 Fuzzy Spatial Filter for Noise Removal.

10.10 Smoothing Algorithm.

10.11 Fuzzy Histogram Modeling.

10.11.1Fuzzy histogram Specification Based on Local.

Information.

10.11.2Fuzzy Histogram Modeling Predicting Missing or.

Imprecise Grey Levels.

10.12 Image Segmentation using Fuzzy Methods.

10.12.1 Image Segmentation by Fuzzy Methods.

10.13 Fuzzy C Means Algorithm.

10.14 Fuzzy Approaches to Pattern Recognition.

10.15 Fusion of fuzzy logic with neural networks.

10.15.1Fuzzy MLP with back propagation learning.

10.16 Summary.

References.

11. Image Mining and Content Based Image Retreival.

11.1 Introduction.

11.2 Representation of images in a CBIR System.

11.2.1 Color Histogram based representation.

11.2.2 Partition based representation.

11.2.3 Regional Approach for image representation.

11.3 Model of a image retrieval system.

11.4 Image Mining.

11.4.1 Color features.

11.4.2 Texture features.

11.4.3 Shape features.

11.4.4 Topology.

11.4.5 Multidimensional indexing.

11.4.6 Results of a simple CBIR system.

11.5 Video Mining.

11.5.1 MPEG-7: Multimedia content description interface.

11.5.2 Content-based video retrieval system.

11.6 Summary.

References.

12. Biometric And Biomedical Image Processing.

12.1 Introduction.

12.2 Face Recognition.

12.2.1 Feature selection.

12.2.2 Extraction of front facial features.

12.2.3 Extraction of side facial features.

12.2.4 Extraction of features.

12.2.5 Face Identification.

12.3 Face Recognition Using Eigenfaces.

12.4 Signature Verification.

12.5 Preprocessing of Signature Patterns.

12.5.1 Feature Extraction.

12.6 Biomedical Image Analysis.

12.6.1 Macroscopic Image Analysis.

12.7 X - ray Image Analysis.

12.7.1 Bone disease Identification.

12.8 Uses of X-ray images.

12.9 Biomedical Imaging Techniques.

12.9.1 Magnetic Resonance Imaging (MRI).

12.9.2 Computed Axial Tomography.

12.9.3 x-ray images for lung disease identification.

12.9.4 x-ray images for Heart disease identification.

12.9.5 x-ray images for Congenital Heart Disease.

12.9.6 Enhancement of chest radiographs using gradient operators.

12.9.7 Adaptive Image Enhancement for Enhancement for chest X-ray images.

12.9.8 A Fuzzy based image enhancement technique for chest radiographs.

12.10 Dental x-ray image analysis.

12.10.1 classification of dental caries.

12.11 Mammogram Image Analysis.

12.11.1 Enhancement of Mammograms.

12.11.2 Smoothing algorithm.

12.11.3 Suspicious Area Detection.

12.11.4 Feature Selection and Extraction.

12.11.5 Important Features of the System.

12.11.6 Wavelet analysis of medical mammogram image.

12.12 Research direction.

12.13 Summary.

References.

13. Remotely Sensed Multispectral Scene Analysis.

13.1 Introduction.

13.2 Satellite sensors and imageries.

13.3 Features of Multispectral Images.

13.3.1 Data Formats For Digital Satellite Imagery.

13.3.2 Distortions and Corrections.

13.4 Spectral reflectance of various earth objects.

13.4.1 Water regions.

13.4.2 Vegetation Regions.

13.4.3 Soil.

13.4.4 Man-made/Artificial Objects.

13.5 Scene Classification Strategies.

13.5.1 Neural Network based Classifier using Error Back Propagation.

13.5.2 Counter propagation network.

13.5.3 Experiments and Results.

13.6 Spectral classification - A knowledge Based Approach.

13.6.1 Spectral information of natural/man-made objects.

13.6.2 Training site selection and feature extraction.

13.6.3 System Implementation.

13.6.4 Feature representation.

13.6.5 Rule Based Development.

13.7 Spatial Reasoning.

13.7.1 Evidence Accumulation.

13.7.2 Spatial rule Generation.

13.8 Fuzzy Set Theoretic Approaches in Remote Sensing.

13.9 Summary.

References.

14. Dynamic Scene Analysis: Moving Object Detection and Tracking.

14.1 Introduction.

14.2 Problem Definition.

14.3 Adaptive Background Modelling.

14.3.1 Basic Background modelling strategy.

14.3.2 A Robust Method of Background Modelling.

14.3.3 Background Model Estimation.

14.4 Connected Component Labeling.

14.5 Shadow Detection.

14.6 Principles of object Tracking.

14.7 Model of Tracker System.

14.8 Condensation Algorithm.

14.9 Particle Filter Based object Tracking.

14.9.1 Particle Attributes.

14.9.2 Particle Filter Algorithm.

14.9.3 Results of Object Tracking.

14.10 Summary.

References.

15. Introduction to Image Compression.

15.1 Introduction.

15.2 Information Theory Concepts.

15.2.1 Discrete Memoryless Model and Entropy.

15.2.2 Noiseless Source Coding Theorem.

15.2.3 Unique Decipherability.

15.3 Classification of Compression algorithms.

15.4 Source Coding Algorithms.

15.4.1 Run-length Coding.

15.5 Huffman Coding.

15.6 Arithmetic Coding.

15.6.1 Encoding Algorithm.

15.6.2 Decoding Algorithm.

15.6.3 The QM-Coder.

15.7 Summary.

References.

16. JPEG: Still Image Compression Standard.

16.1 Introduction.

16.2 The JPEG Lossless Coding Algorithm.

16.3 Baseline JPEG Compression.

16.3.1 Color Space Conversion.

16.3.2 Source Image Data Arrangement.

16.3.3 The Baseline Compression Algorithm.

16.3.4 Coding the DCT Coefficients.

16.4 Summary.

References.

17. JPEG2000 Standard.

17.1 Introduction.

17.2 Why JPEG2000?

17.3 Parts of the JPEG2000 Standard.

17.4 Overview of the JPEG2000 Part 1 Encoding System.

17.5 Image Preprocessing.

17.5.1 Tiling.

17.5.2 DC Level Shifting.

17.5.3 Multi-component Transformations.

17.6 Compression.

17.6.1 Discrete Wavelet Transformation.

17.6.2 Quantization.

17.6.3 Region of Interest Coding.

17.6.4 Rate Control.

17.6.5 Entropy Encoding.

17.7 Tier-2 Coding and Bitstream Formation.

17.8 Summary.

References.

18. Coding Algorithms in JPEG2000.

18.1 Introduction.

18.2 Partitioning Data for Coding.

18.3 Tier-1 Coding in JPEG2000.

18.3.1 Fractional Bit-Plane Coding.

18.3.2 Examples of BPC Encoder.

18.3.3 Binary Arithmetic Coding--MQ-Coder.

18.4 Tier-2 Coding in JPEG2000.

18.4.1 Bitstream Formation.

18.4.2 Packet Header Information Coding.

18.5 Summary.

References.

Index.

About the Authors.