Document Layout Analysis (SpringerBriefs in Computer Science)

✍ Scribed by Showmik Bhowmik

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 92
• Edition: 1st ed. 2023
• Category: Library

✦ Synopsis

Document layout analysis (DLA) is a crucial step towards the development of an effective document image processing system. In the early days of document image processing, DLA was not considered as a complete and complex research problem, rather just a pre-processing step having some minor challenges. The main reason for that is the type of layout being considered for processing was simple. Researchers started paying attention to this complex problem as they come across a large variety of documents. This book presents a clear view of the past, present, and future of DLA, and it also discusses two recent methods developed to address the said problem.

✦ Table of Contents

Preface
Contents
Chapter 1: Introduction
1.1 Document Image Processing System
1.2 Structure of a Document
1.3 Categories of Document Layout
1.4 Document Layout Analysis (DLA)
1.5 Why DLA Is Still an Open Area of Research
References
Chapter 2: Document Image Binarization
2.1 Different Types of Degradations and Noise
2.2 Pre-processing
2.3 Document Image Binarization
2.4 Different Binarization Methods
2.4.1 Threshold-Based Methods
2.4.2 Optimization Based Methods
2.4.3 Classification-Based Methods
2.5 Evaluation Techniques
2.5.1 Standard Databases for DIB
2.5.2 Performance Metrics
F-Measure (FM)
Peak Signal-to-Noise Ratio (PSNR)
Distance Reciprocal Distortion (DRD)
Pseudo-F-Measure (PseudoFM)
References
Chapter 3: Document Region Segmentation
3.1 Different Document Region Segmentation Methods
3.1.1 Pixel Analysis-Based Methods
3.1.2 Connected Component Analysis-Based Methods
3.1.3 Local Region Analysis-Based Methods
3.1.4 Hybrid Methods
3.2 Available Dataset for Page Segmentation
3.3 Evaluation Metrices
References
Chapter 4: Document Region Classification
4.1 Different Types of Document Regions
4.2 Different Document Region Classification Methods
4.2.1 Methods for Text/Non-text Classification
Non-machine Learning Based Methods
Shallow Learning Based Methods
Deep Learning Based Methods
4.2.2 Methods for Text Region Classification
4.2.3 Methods for Non-text Classification
Table Detection
Chart Processing
4.3 Evaluation Techniques
4.3.1 Standard Datasets
4.3.2 Evaluation Metrices
References
Chapter 5: Case Study
5.1 Analysis of Basic Contents in Documents (ABCD)
5.1.1 Pre-processing
5.1.2 Non-text Suppression and Noise Removal
5.1.3 Text Region Generation
Region Generation
Region Refinement
5.1.4 Non-text Classification
Identification of Separator and Margin
Identification of Table
5.1.5 Experimental Results
5.2 BINYAS
5.2.1 Pre-processing
5.2.2 Isolation of Separators
5.2.3 Layout Complexity Estimation
5.2.4 Separation of Large and Small Components
5.2.5 Text and Non-text Separation
5.2.6 Thickness Based Text Separation
5.2.7 Text Region Segmentation
5.2.8 Non-text Classification
References
Chapter 6: Summary
References