Handbook of Document Image Processing and Recognition

ISBN-13: 9780857298584 / Angielski / Twarda / 2014 / 1055 str.

David Doermann; Karl Tombre

Opis

The Handbook of Document Image Processing and Recognition is a comprehensive resource on the latest methods and techniques in document image processing and recognition. Each chapter provides a clear overview of the topic followed by the state of the art of techniques used - including elements of comparison between them - along with supporting references to archival publications, for those interested in delving deeper into topics addressed. Rather than favor a particular approach, the text enables the reader to make an informed decision for their specific problems.

Recenzje

From the book reviews:

"This edited compendium of chapters represents the largest effort to date to bring together the breadth and depth of image processing research for document text extraction, segmentation of document image into picture and text zones, and general optical character recognition (OCR) of the international family of foreign languages. ... will appeal to the widest audience possible, including academicians, practitioners, library science and legal professionals, and all who are interested in the efficient storage and retrieval of vast numbers of documents." (R. Goldberg, Computing Reviews, October, 2014)

Spis treści

A Brief History of Documents and Writing Systems.- Machine-printed Character Recognition.- Handprinted Character and Word Recognition.- Continuous Handwritten Script Recognition.- Middle Eastern Character Recognition.- Asian Character Recognition.- Graphics Recognition Techniques.- An Overview of Symbol Recognition.- Analysis and Interpretation of Graphical Documents.- Logo and Trademark Recognition.- Recognition of Tables and Forms.- Document Creation, Image Acquisition and Document Quality.- Processing Mathematical Notation.- Document Analysis in Postal Applications and Check Processing.- Analysis and Recognition of Music Scores.- Analysis of Documents Born Digital.- Image Based Retrieval and Keyword.-  Spotting in Documents.- Text Localization and Recognition in Images and Video.- Online Handwriting Recognition.- Online Signature Verification.- Sketching Interfaces.- Datasets and Annotations for Document Analysis and Recognition.- The Evolution of Document Image Analysis.- Tools and Metrics for Document Analysis Systems Evaluation.- Imaging Techniques in Document Analysis Processes.- Page Segmentation Techniques in Document Analysis.- Analysis of the Logical Layout of Documents.- Page Similarity and Classification.- Text Segmentation for Document Recognition.- Language, Script and Font Recognition.- Part A, Introduction, Background and Fundamentals.- Part B, Page Analysis.- Part C, Text Recognition.- Part D, Processing of Non-textual Information.- Part E, Applications.- Part F, Analysis of Online Data.- Part G, Evaluation and Benchmarking.

O autorze

Dr. David Doermann is Senior Research Scientist and Director of the Laboratory for Language and Media Processing at the University of Maryland Institute for Advanced Computer Studies, College Park, MD, USA. He is also President and co-founder of Applied Media Analysis, Inc., and Editor-in-Chief of the International Journal on Document Analysis and Recognition.

Dr. Karl Tombre is Professor at Université de Lorraine, France, one of the lagest French universities, where he currently is vice-president in charge of partnerships and international affairs. He was one of the founders, and for many years an editor-in-chief of the International Journal on Document Analysis and Recognition. From 2007 to 2012 he was director of the Inria Nancy - Grand Est research center, a large public research center in computer science and applied mathematics. From 2006 to 2008 he was President of the International Association for Pattern Recognition (IAPR).

Blurb

The Handbook of Document Image Processing and Recognition provides a consistent, comprehensive resource on the available methods and techniques in document image processing and recognition. It includes unified comparison and contrast analysis of algorithms in standard table formats. Thus, it educates the reader in order to help them to make informed decisions on their particular problems.

The handbook is divided into several parts. Each part starts with an introduction written by the two editors. These introductions set the general framework for the main topic of each part and introduces the contribution of each chapter within the framework. The introductions are followed by several chapters written by established experts of the field.

Each chapter provides the reader with a clear overview of the topic and of the state of the art in techniques used (including elements of comparison between them). Each chapter is structured in the same way: It starts with an introductory text, concludes with a summary of the main points addressed in the chapter and ends with a comprehensive list of references. Whenever appropriate, the authors include specific sections describing and pointing to consolidated software and/or reference datasets. Numerous cross-references between the chapters ensure this is a truly integrated work, without unnecessary duplications and overlaps between chapters.

This reference work is intended for the use by a wide audience of readers from around the world such as graduate students, researchers, librarians, lecturers, professionals, and many other people.