Machine Learning in Document Analysis and Recognition

1. Front Matter

   Pages I-XI

   PDF

2. Introduction to Document Analysis and Recognition

   • Simone Marinai

   Pages 1-20

3. Structure Extraction in Printed Documents Using Neural Approaches

   • Abdel Belaïd, Yves Rangoni

   Pages 21-43

4. Machine Learning for Reading Order Detection in Document Image Understanding

   • Donato Malerba, Michelangelo Ceci, Margherita Berardi

   Pages 45-69

5. Decision-Based Specification and Comparison of Table Recognition Algorithms

   • Richard Zanibbi, Dorothea Blostein, James R. Cordy

   Pages 71-103

6. Machine Learning for Digital Document Processing: from Layout Analysis to Metadata Extraction

   • Floriana Esposito, Stefano Ferilli, Teresa M. A. Basile, Nicola Di Mauro

   Pages 105-138

7. Classification and Learning Methods for Character Recognition: Advances and Remaining Problems

   • Cheng-Lin Liu, Hiromichi Fujisawa

   Pages 139-161

8. Combining Classifiers with Informational Confidence

   • Stefan Jaeger, Huanfeng Ma, David Doermann

   Pages 163-191

9. Self-Organizing Maps for Clustering in Document Image Analysis

   • Simone Marinai, Emanuele Marino, Giovanni Soda

   Pages 193-219

10. Adaptive and Interactive Approaches to Document Analysis

    • George Nagy, Sriharsha Veeramachaneni

    Pages 221-257

11. Cursive Character Segmentation Using Neural Network Techniques

    • Michael Blumenstein

    Pages 259-275

12. Multiple Hypotheses Document Analysis

    • Tatsuhiko Kagehiro, Hiromichi Fujisawa

    Pages 277-303

13. Learning Matching Score Dependencies for Classifier Combination

    • Sergey Tulyakov, Venu Govindaraju

    Pages 305-332

14. Perturbation Models for Generating Synthetic Training Data in Handwriting Recognition

    • Tamás Varga, Horst Bunke

    Pages 333-360

15. Review of Classifier Combination Methods

    • Sergey Tulyakov, Stefan Jaeger, Venu Govindaraju, David Doermann

    Pages 361-386

16. Machine Learning for Signature Verification

    • Sargur N. Srihari, Harish Srinivasan, Siyuan Chen, Matthew J. Beal

    Pages 387-408

17. Off-line Writer Identification and Verification Using Gaussian Mixture Models

    • Andreas Schlapbach, Horst Bunke

    Pages 409-428

18. Back Matter

    Pages 429-433

    PDF

The objective of Document Analysis and Recognition (DAR) is to recognize the text and graphicalcomponents of a document and to extract information. With ?rst papers dating back to the 1960’s, DAR is a mature but still gr- ing research?eld with consolidated and known techniques. Optical Character Recognition (OCR) engines are some of the most widely recognized pr- ucts of the research in this ?eld, while broader DAR techniques are nowadays studied and applied to other industrial and o?ce automation systems. In the machine learning community, one of the most widely known - search problems addressed in DAR is recognition of unconstrained handwr- ten characters which has been frequently used in the past as a benchmark for evaluating machine learning algorithms, especially supervised classi?ers. However, developing a DAR system is a complex engineering task that involves the integration of multiple techniques into an organic framework. A reader may feel that the use of machine learning algorithms is not approp- ate for other DAR tasks than character recognition. On the contrary, such algorithms have been massively used for nearly all the tasks in DAR. With large emphasis being devoted to character recognition and word recognition, other tasks such as pre-processing, layout analysis, character segmentation, and signature veri?cation have also bene?ted much from machine learning algorithms.

• Document Image Analysis and Recognition (DIAR)
• Learning Strategies
• algorithm
• algorithms
• calculus
• classification
• cognition
• handwriting recognition
• image analysis
• layout
• learning
• machine learning
• neural networks
• self-organizing map
• verification

• Dipartimento di Sistemi e Informatica, University of Florence, Firenze, Italy

  Simone Marinai

• Hitachi Central Research Laboratory, Kokubunji-shi, Tokyo, Japan

  Hiromichi Fujisawa

Policies and ethics