: B. Chaudhuri
: Bidyut B. Chaudhuri
: Digital Document Processing Major Directions and Recent Advances
: Springer-Verlag
: 9781846287268
: Advances in Computer Vision and Pattern Recognition
: 1
: CHF 135.30
:
: Anwendungs-Software
: English
: 464
: Wasserzeichen
: PC/MAC/eReader/Tablet
: PDF

This book brings all the major and frontier topics in the field of document analysis together into a single volume, creating a unique reference source that will be invaluable to a large audience of researchers, lecturers and students working in this field. With chapters written by some of the most distinguished researchers active in this field, this book addresses recent advances in digital document processing research and development.

Preface6
Contents8
Contributors17
1 Reading Systems: An Introduction to Digital Document Processing20
1.1 Introduction20
1.2 Text Sensing22
1.3 Sensor Scope22
1.4 Sensor Grid25
1.5 Pre-processing25
1.6 Invariance to Affine Transforms26
1.7 Invariance to Ink-Trace Thickness28
1.8 Shape Features29
1.9 Processing Type31
1.10 Computing Architecture32
1.11 Computing Strategy32
1.12 Knowledge Base33
1.13 Cognitive Reliability34
1.14 Response in Case of Difficult Input34
1.15 Classification Accuracy35
1.16 Energy and Mental Concentration36
1.17 Processing Speed36
1.18 Volume Processing36
1.19 Summary of Human Versus Machine Reading37
1.20 Conclusion45
References45
2 Document Structure and Layout Analysis48
2.1 Introduction48
2.2 Pre-processing50
2.3 Representing Document Structure and Layout53
2.4 Document Layout Analysis55
2.5 Understanding Document Structure61
2.6 Performance Evaluation62
2.7 Handwritten Document Analysis64
2.8 Summary65
References66
3 OCR Technologies for Machine Printed and Hand Printed Japanese Text68
3.1 Introduction68
3.2 Pre-Processing68
3.3 Feature Extraction77
3.4 Classification80
3.5 Dimension Reduction82
3.6 Performance Evaluation of OCR Technologies83
3.7 Learning Algorithms86
3.8 Conclusion88
References89
4 Multi-Font Printed Tibetan OCR91
4.1 Introduction91
4.2 Properties of Tibetan Characters and Scripts92
4.3 Isolated Tibetan Character Recognition96
4.4 Tibetan Document Segmentation106
4.5 Experiment Results112
4.6 Summary114
Acknowledgments114
References114
5 On OCR of a Printed Indian Script117
5.1 Introduction117
5.2 Origin and Properties of Indian Scripts118
5.3 Document Pre-Processing122
5.4 Character Recognition125
5.5 Performance Analysis132
5.6 Conclusion135
Acknowledgments135
References136
6 A Bayesian Network Approach for On-line Handwriting Recognition138
6.1 Introduction138
6.2 Modelling of Character Components and Their Relationships141
6.3 Recognition and Training Algorithms147
6.4 Experimental Results and Analysis149
6.5 Conclusions156
References157
7 New Advances and New Challenges in On- Line Handwriting Recognition and Electronic Ink Management159
7.1 Introduction159
7.2 On-Line Handwriting Recognition Systems160
7.3 New Trends in On-Line Handwriting Recognition160
7.4 New Trends in Electronic Ink Management Systems164
7.5 Conclusion, Open Problems and New Challenges172
References173
8 Off-Line Roman Cursive Handwriting Recognition181
8.1 Introduction181
8.2 Methodology182
8.3 Emerging Topics187
8.4 Outlook and Conclusions191
Acknowledgment192
References192
9 Robustness Design of Industrial Strength Recognition Systems200
9.1 Characterization of Robustness200
9.2 Complex Recognition System: Postal Address Recognition202
9.3 Performance Influencing Factors204
9.4 Robustness Design Principles209
9.5 Robustness Strategy for Implementation218
9.6 Conclusions224
Acknowledgments224
References225
10 Arabic Cheque Processing System: Issues and Future Trends228
10.1 Introduction228
10.2 Datasets229
10.3 Legal Amount Processing230
10.4 Courtesy Amount Processing237
10.5 Conclusion and Future Perspective245
References247
11 OCR of Printed Mathematical Expressions250
11.1 Introduction250
11.2 Identification of Expressions in Document Images252
11.3 Recognition of Expression Symbols256
11.4 Interpretation of Expression Structure260
11.5 Performance Evaluation266
11.6 Conclusion and Future Research270
References271
12 The State of the Art of Document Image Degradation Modelling275
12.1 Introduction275
12.2 Document Image Degradations276
12.3 The Measurement of Image Quality278
12.4 Document Image Degradation Models280
12.5 Applications of Models284
12.6 Public-Domain Software and Image Databases286
12.7 Open Problems287
Acknowledgments289
References289
13 Advances in Graphics Recognition294
13.1 Introduction294
13.2 Application Scenarios297
13.3 Early Processing300
13.4 Symbol Recognition and Indexing301
13.5 Architectures and Meta-data Modelling302
13.6 On-Line Graphics Recognition and Sketching Interfaces304
13.7 Performance Evaluation306
13.8 An Application Scenario: Interpretation of Architectural Sketches307
13.9 Conclusions: Sketching the Future308
Acknowledgment310
Reference