Atnaujinkite slapukų nuostatas

Document Analysis And Recognition With Wavelet And Fractal Theories [Kietas viršelis]

(University Of Macau, China)
Kitos knygos pagal šią temą:
Document Analysis And Recognition With Wavelet And Fractal TheoriesDidesnis paveikslėlis
Kitos knygos pagal šią temą:
Pastovi nuoroda: https://www.kriso.lt/db/9789814401005.html
Raktažodžiai:
Many phenomena around the research in document analysis and understanding are much better described through the powerful multiscale signal representations than by traditional ways.From this perspective, the recent emergence of powerful multiscale signal representations in general and fractal/wavelet basis representations in particular, has been particularly timely. Indeed, out of these theories arise highly natural and extremely useful representations for a variety of important phenomena in document analysis and understanding.This book presents both the development of these new approaches as well as their application to a number of fundamental problems of interest to scientists and engineers in document analysis and understanding.
Preface vii
Chapter 1 Basic Concepts of Document Analysis and Understanding
1(54)
1.1 Introduction
1(3)
1.2 Basic Model of Document Processing
4(4)
1.3 Document Structures
8(5)
1.3.1 Strength of Structure
8(1)
1.3.2 Geometric Structure
9(1)
1.3.2.1 Geometric Complexity
10(2)
1.3.3 Logical Structure
12(1)
1.4 Document Analysis
13(10)
1.4.1 Hierarchical Methods
13(1)
1.4.1.1 Top-Down Approach
14(2)
1.4.1.2 Bottom-Up Approach
16(1)
1.4.2 No-Hierarchical Methods
17(1)
1.4.2.1 Modified Fractal Signature
18(2)
1.4.2.2 Order Stochastic Filtering
20(2)
1.4.3 Web Document Analysis
22(1)
1.5 Document Understanding
23(4)
1.5.1 Document Understanding Based on Tree Transformation
24(1)
1.5.2 Document Understanding Based on Formatting Knowledge
25(1)
1.5.3 Document Understanding Based on Description Language
26(1)
1.6 Form Document Processing
27(5)
1.6.1 Characteristics of Form Documents
27(1)
1.6.2 Wavelet Transform Approach
27(1)
1.6.3 Approach Based on Form Description Language
28(3)
1.6.4 Form Document Processing Based on Form Registration
31(1)
1.6.5 Form Document Processing System
31(1)
1.7 Character Recognition and Document Image Processing
32(11)
1.7.1 Handwritten and Printed Character Recognition
32(1)
1.7.1.1 Extracting Multiresolution Features in Recognition of Handwritten Numerals with 2-D Haar Wavelet
33(4)
1.7.1.2 Recognition of Printed Kannada Text in Indian Languages
37(1)
1.7.1.3 Wavelet Descriptors of Handprinted Characters
38(1)
1.7.2 Document Image Analysis Based on Multiresolution Hadamard Representation (MHR)
38(5)
1.8 Major Techniques
43(12)
1.8.1 Hough Transform
44(1)
1.8.2 Techniques for Skew Detection
45(1)
1.8.3 Projection Profile Cuts
46(1)
1.8.4 Run-Length Smoothing Algorithm (RLSA)
47(1)
1.8.5 Neighborhood Line Density (NLD)
48(1)
1.8.6 Connected Components Analysis (CCA)
49(1)
1.8.7 Crossing Counts
50(1)
1.8.8 Form Definition Language (FDL)
50(1)
1.8.9 Texture Analysis -- Gabor Filters
51(1)
1.8.10 Wavelet Transform
52(1)
1.8.11 Other Segmentation Techniques
53(2)
Chapter 2 Basic Concepts of Fractal Dimension
55(40)
2.1 Definitions of Fractals
55(2)
2.2 Hausdorff Dimension
57(12)
2.2.1 Hausdorff Measure
57(3)
2.2.2 Hausdorff Dimension
60(4)
2.2.3 Examples of Computing Hausdorff Dimension
64(5)
2.3 Box Computing Dimension
69(14)
2.3.1 Dimensions
69(1)
2.3.2 Box Computing Dimension
70(5)
2.3.3 Minkowski Dimension
75(6)
2.3.4 Properties of Box Counting Dimension
81(2)
2.4 Basic Methods for Calculating Dimensions
83(12)
Chapter 3 Basic Concepts of Wavelet Theory
95(78)
3.1 Continuous Wavelet Transforms
95(29)
3.1.1 General Theory of Continuous Wavelet Transforms
95(16)
3.1.2 The Continuous Wavelet Transform as a Filter
111(3)
3.1.3 Description of Regularity of Signal by Wavelet
114(4)
3.1.4 Some Examples of Basic Wavelets
118(6)
3.2 Multiresolution Analysis (MRA) and Wavelet Bases
124(49)
3.2.1 Multiresolution Analysis
124(1)
3.2.1.1 Basic Concept of MRA
124(5)
3.2.1.2 The Solution of Two-Scale Equation
129(10)
3.2.2 The Construction of MRAs
139(7)
3.2.2.1 The Biorthonormal MRA
146(7)
3.2.2.2 Examples of Constructing MRA
153(10)
3.2.3 The Construction of Biorthonormal Wavelet Bases
163(5)
3.2.4 S. Mallat Algorithms
168(5)
Chapter 4 Document Analysis by Fractal Dimension
173(30)
4.1 Introduction
173(6)
4.2 Document Analysis Based on Modified Fractal Signature (MFS)
179(8)
4.2.1 Basic Idea of Modified Fractal Signature (MFS)
179(1)
4.2.2 δ-Parallel Bodies
180(3)
4.2.3 Blanket Technique to Extract Fractal Feature
183(4)
4.3 Algorithm of Modified Fractal Signature (MFS)
187(7)
4.3.1 Identification of Different Blocks of Document by Fractal Signature
187(4)
4.3.2 Modified Fractal Signature (MFS)
191(3)
4.4 Experiments
194(9)
Chapter 5 Text Extraction by Wavelet Decomposition
203(28)
5.1 Introduction
203(1)
5.2 Wavelet Decomposition of Pseudo-Motion Functions
204(5)
5.2.1 One Variable Case
204(4)
5.2.2 Two Variables Case
208(1)
5.3 Segmentation of Different Areas of Document Image
209(6)
5.3.1 Segmentation of Areas of Different Frequency
209(3)
5.3.2 WDPM Algorithm
212(3)
5.4 Experiments
215(16)
5.4.1 Position of License Plate
215(1)
5.4.1.1 Choose of the Bases
215(4)
5.4.1.2 Experimental Results
219(1)
5.4.2 Localization of Text Areas of Document Images
220(11)
Chapter 6 Rotation Invariant by Fractal Theory with Central Projection Transform (CPT)
231(48)
6.1 Introduction
231(13)
6.1.1 Rotations
232(2)
6.1.2 Rotation Invariants
234(3)
6.1.3 Rotation Invariant of Discrete Images
237(4)
6.1.4 Rotation Invariants in Pattern Recognition
241(1)
6.1.4.1 Boundary Curvature
242(1)
6.1.4.2 Fourier Descriptors
242(1)
6.1.4.3 Zernik Moments
243(1)
6.1.4.4 Neural Networks
243(1)
6.2 Preprocessing and Central Projection Transform (CPT)
244(12)
6.2.1 Preprocessing
244(2)
6.2.2 Central Projection Transform (CPT)
246(1)
6.2.2.1 Basic Definitions of CPT
246(4)
6.2.2.2 Properties of CPT
250(2)
6.2.2.3 Parallel Algorithm for CPT
252(1)
6.2.2.4 Contour Unfolding
253(3)
6.3 Rotation Invariance Based on Box Computing Dimension
256(11)
6.3.1 Estimation of the 1-D Fractal Dimension
256(2)
6.3.2 Rotation Invariant Signature (RIS)
258(9)
6.4 Experiments
267(12)
6.4.1 Rotation Invariant Signature (RIS) Algorithm
267(1)
6.4.1.1 Estimation of the BCD
267(2)
6.4.1.2 Extraction of Feature with Rotation Invariant Property
269(2)
6.4.2 Experimental Procedure and Results
271(8)
Chapter 7 Wavelet-Based and Fractal-Based Methods for Script Identification
279(30)
7.1 Introduction
280(2)
7.2 Wavelet-Based Approach
282(18)
7.2.1 Image Decomposition by Multi-Scale Wavelet Transform
284(3)
7.2.2 Wavelet-Based Features
287(1)
7.2.2.1 Average Energy of Document Image
287(2)
7.2.2.2 Wavelet Energy Distribution Features (Fd)
289(2)
7.2.2.3 Wavelet Energy Distribution Proportion Features (Fdp)
291(2)
7.2.3 Experiments
293(1)
7.2.3.1 Distance Functions
293(2)
7.2.3.2 Experimental Results
295(5)
7.3 Fractal-Based Approach
300(9)
7.3.1 Algorithm
301(1)
7.3.2 Experiments
302(7)
Chapter 8 Writer Identification Using Hidden Markov Model in Wavelet Domain (WD-HMM)
309(28)
8.1 Introduction
309(1)
8.2 Hidden Markov Model and Relative Statistical Knowledge
310(10)
8.2.1 Expectation Maximization (EM) Algorithm
310(2)
8.2.2 Gaussian Mixture Model (GMM) and Expectation Maximization (EM) for Gaussian Mixture Model (GMM)
312(4)
8.2.3 Hidden Markov Model
316(1)
8.2.3.1 Basic Frame of HMM
316(2)
8.2.3.2 Three Basic Problems for HMM
318(1)
8.2.3.3 Important Assumptions for HMM
319(1)
8.3 Hidden Markov Models in Wavelet Domain
320(4)
8.3.1 GMM Model for a Single Wavelet Coefficient
320(1)
8.3.2 Independence Mixture Model
320(1)
8.3.3 WD-HMM and EM for WD-HMM
321(3)
8.4 Writer Identification Using WD-HMM
324(5)
8.4.1 The Whole Procedure
324(1)
8.4.2 Feature Extraction
325(1)
8.4.3 Similarity Measurement
326(3)
8.4.4 Performance Evaluation
329(1)
8.5 Experiments
329(8)
Bibliography 337(16)
Index 353