Record:   Prev Next
Author Tang, Yuan Yan
Title Document Analysis and Recognition with Wavelet and Fractal Theories
Imprint Singapore : World Scientific Publishing Co Pte Ltd, 2012
©2012
book jacket
Descript 1 online resource (373 pages)
text txt rdacontent
computer c rdamedia
online resource cr rdacarrier
Series World Scientific Series On The Economics Of Climate Change ; v.79
World Scientific Series On The Economics Of Climate Change
Note Intro -- Contents -- Preface -- Chapter 1 Basic Concepts of Document Analysis and Understanding -- 1.1 Introduction. -- 1.2 Basic Model of Document Processing -- 1.3 Document Structures -- 1.3.1 Strength of Structure -- 1.3.2 Geometric Structure -- 1.3.2.1 Geometric Complexity -- 1.3.3 Logical Structure -- 1.4 Document Analysis -- 1.4.1 Hierarchical Methods -- 1.4.1.1 Top-Down Approach -- 1.4.1.2 Bottom-Up Approach -- 1.4.2 No-HierarchicalMethods -- 1.4.2.1 Modified Fractal Signature -- 1.4.2.2 Order Stochastic Filtering -- 1.4.3 Web Document Analysis -- 1.5 Document Understanding -- 1.5.1 Document Understanding Based on Tree Transformation -- 1.5.2 Document Understanding Based on Formatting Knowledge -- 1.5.3 Document Understanding Based on Description Language -- 1.6 Form Document Processing -- 1.6.1 Characteristics of Form Documents -- 1.6.2 Wavelet Transform Approach -- 1.6.3 Approach Based on Form Description Language -- 1.6.4 Form Document Processing Based on Form Registration -- 1.6.5 Form Document Processing System -- 1.7 Character Recognition and Document Image Processing -- 1.7.1 Handwritten and Printed Character Recognition -- 1.7.1.1 Extracting Multiresolution Features in Recognition of Handwritten Numerals with 2-D Haar Wavelet -- 1.7.1.2 Recognition of Printed Kannada Text in Indian Languages -- 1.7.1.3 Wavelet Descriptors of Handprinted Characters -- 1.7.2 Document Image Analysis Based on Multiresolution Hadamard Representation (MHR) -- 1.8 Major Techniques -- 1.8.1 Hough Transform. -- 1.8.2 Techniques for Skew Detection -- 1.8.3 Projection Profile Cuts -- 1.8.4 Run-Length Smoothing Algorithm (RLSA) -- 1.8.5 Neighborhood Line Density (NLD) -- 1.8.6 Connected Components Analysis (CCA) -- 1.8.7 Crossing Counts -- 1.8.8 Form Definition Language (FDL) -- 1.8.9 Texture Analysis - Gabor Filters -- 1.8.10 Wavelet Transform
1.8.11 Other Segmentation Techniques -- Chapter 2 Basic Concepts of Fractal Dimension -- 2.1 Definitions of Fractals -- 2.2 Hausdorff Dimension -- 2.2.1 Hausdorff Measure -- 2.2.2 Hausdorff Dimension -- 2.2.3 Examples of Computing Hausdorff Dimension -- 2.3 Box Computing Dimension -- 2.3.1 Dimensions -- 2.3.2 Box Computing Dimension -- 2.3.3 Minkowski Dimension -- 2.3.4 Properties of Box Counting Dimension -- 2.4 Basic Methods for Calculating Dimensions -- Chapter 3 Basic Concepts of Wavelet Theory -- 3.1 Continuous Wavelet Transforms -- 3.1.1 General Theory of Continuous Wavelet Transforms -- 3.1.2 The Continuous Wavelet Transform as a Filter -- 3.1.3 Description of Regularity of Signal by Wavelet -- 3.1.4 Some Examples of Basic Wavelets -- 3.2 Multiresolution Analysis (MRA) and Wavelet Bases -- 3.2.1 Multiresolution Analysis -- 3.2.1.1 Basic Concept of MRA -- 3.2.1.2 The Solution of Two-Scale Equation -- 3.2.2 The Construction of MRAs -- 3.2.2.1 The Biorthonormal MRA -- 3.2.2.2 Examples of Constructing MRA -- 3.2.3 The Construction of Biorthonormal Wavelet Bases -- 3.2.4 S.Mallat Algorithms -- Chapter 4 Document Analysis by Fractal Dimension -- 4.1 Introduction. -- 4.2 Document Analysis Based on Modified Fractal Signature (MFS) -- 4.2.1 Basic Idea of Modified Fractal Signature (MFS) -- 4.2.2 δ-Parallel Bodies -- 4.2.3 Blanket Technique to Extract Fractal Feature -- 4.3 Algorithm of Modified Fractal Signature (MFS) -- 4.3.1 Identification of Different Blocks of Document by Fractal Signature -- 4.3.2 Modified Fractal Signature (MFS) -- 4.4 Experiments -- Chapter 5 Text Extraction by Wavelet Decomposition -- 5.1 Introduction -- 5.2 Wavelet Decomposition of Pseudo-Motion Functions -- 5.2.1 One Variable Case -- 5.2.2 Two Variables Case -- 5.3 Segmentation of Different Areas of Document Image -- 5.3.1 Segmentation of Areas of Different Frequency
5.3.2 WDPM Algorithm -- 5.4 Experiments -- 5.4.1 Position of License Plate -- 5.4.1.1 Choose of the Bases -- 5.4.1.2 Experimental Results -- 5.4.2 Localization of Text Areas of Document Images -- Chapter 6 Rotation Invariant by Fractal Theory with Central Projection Transform (CPT) -- 6.1 Introduction -- 6.1.1 Rotations -- 6.1.2 Rotation Invariants -- 6.1.3 Rotation Invariant of Discrete Images -- 6.1.4 Rotation Invariants in Pattern Recognition -- 6.1.4.1 Boundary Curvature -- 6.1.4.2 Fourier Descriptors -- 6.1.4.3 Zernik Moments -- 6.1.4.4 Neural Networks -- 6.2 Preprocessing and Central Projection Transform (CPT) -- 6.2.1 Preprocessing -- 6.2.2 Central Projection Transform (CPT) -- 6.2.2.1 Basic Definitions of CPT -- 1. Central Projection -- 2. Regional Central Projection (RCP) -- 6.2.2.2 Properties of CPT -- 1. Contour Unitization -- 2. Shape Invariance -- 6.2.2.3 Parallel Algorithm for CPT -- 6.2.2.4 Contour Unfolding -- 6.3 Rotation Invariance Based on Box Computing Dimension -- 6.3.1 Estimation of the 1-D Fractal Dimension -- 6.3.2 Rotation Invariant Signature (RIS) -- 6.4 Experiments -- 6.4.1 Rotation Invariant Signature (RIS) Algorithm -- 6.4.1.1 Estimation of the BCD -- 6.4.1.2 Extraction of Feature with Rotation Invariant Property -- 6.4.2 Experimental Procedure and Results -- Chapter 7 Wavelet-Based and Fractal-Based Methods for Script Identification -- 7.1 Introduction -- 7.2 Wavelet-Based Approach -- 7.2.1 Image Decomposition by Multi-Scale Wavelet Transform -- 7.2.2 Wavelet-Based Features -- 7.2.2.1 Average Energy of Document Image -- 7.2.2.2 Wavelet Energy Distribution Features (Fd) -- 7.2.2.3 Wavelet Energy Distribution Proportion Features (Fdp) -- 7.2.3 Experiments -- 7.2.3.1 Distance Functions -- 7.2.3.2 Experimental Results -- 7.3 Fractal-Based Approach -- 7.3.1 Algorithm -- 7.3.2 Experiments
Chapter 8 Writer Identification Using Hidden Markov Model in Wavelet Domain (WD-HMM) -- 8.1 Introduction -- 8.2 Hidden Markov Model and Relative Statistical Knowledge -- 8.2.1 Expectation Maximization (EM) Algorithm -- 8.2.2 Gaussian Mixture Model (GMM) and Expectation Maximization (EM) for Gaussian Mixture Model (GMM) -- 8.2.3 Hidden Markov Model -- 8.2.3.1 Basic Frame of HMM -- 8.2.3.2 Three Basic Problems for HMM -- 8.2.3.3 Important Assumptions for HMM -- 8.3 Hidden Markov Models in Wavelet Domain -- 8.3.1 GMM Model for a Single Wavelet Coefficient -- 8.3.2 Independence Mixture Model -- 8.3.3 WD-HMM and EM for WD-HMM -- 8.4 Writer Identification Using WD-HMM -- 8.4.1 The Whole Procedure -- 8.4.2 Feature Extraction -- 8.4.3 Similarity Measurement -- 8.4.4 Performance Evaluation -- 8.5 Experiments -- Bibliography -- Index
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
Description based on publisher supplied metadata and other sources
Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2020. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries
Link Print version: Tang, Yuan Yan Document Analysis and Recognition with Wavelet and Fractal Theories Singapore : World Scientific Publishing Co Pte Ltd,c2012 9789814401005
Subject Wavelets (Mathematics);Fractals
Electronic books
Record:   Prev Next