Symbol Spotting in Digital Libraries

Focused Retrieval over Graphic-rich Document Collections

  • Marçal Rusiñol
  • Josep Lladós

Table of contents

  1. Front Matter
    Pages I-XIV
  2. Introduction

    1. Front Matter
      Pages 1-1
    2. Marçal Rusiñol, Josep Lladós
      Pages 3-14
    3. Marçal Rusiñol, Josep Lladós
      Pages 15-47
  3. On the Use of Photometric Descriptors for Symbol Spotting

    1. Front Matter
      Pages 49-49
    2. Marçal Rusiñol, Josep Lladós
      Pages 51-65
  4. On the Use of Geometric and Structural Constraints for Symbol Spotting

    1. Front Matter
      Pages 67-67
    2. Marçal Rusiñol, Josep Lladós
      Pages 69-88
    3. Marçal Rusiñol, Josep Lladós
      Pages 89-111
    4. Marçal Rusiñol, Josep Lladós
      Pages 113-129
  5. A Performance Evaluation Protocol for Symbol Spotting Systems

    1. Front Matter
      Pages 131-131
    2. Marçal Rusiñol, Josep Lladós
      Pages 133-159
    3. Marçal Rusiñol, Josep Lladós
      Pages 161-166
  6. Back Matter
    Pages 167-180

About this book

Introduction

The specific problem of symbol recognition in graphical documents requires additional techniques to those developed for character recognition. The most well-known obstacle is the so-called Sayre paradox: Correct recognition requires good segmentation, yet improvement in segmentation is achieved using information provided by the recognition process. This dilemma can be avoided by techniques that identify sets of regions containing useful information. Such symbol-spotting methods allow the detection of symbols in maps or technical drawings without having to fully segment or fully recognize the entire content.

This unique text/reference provides a complete, integrated and large-scale solution to the challenge of designing a robust symbol-spotting method for collections of graphic-rich documents. The book examines a number of features and descriptors, from basic photometric descriptors commonly used in computer vision techniques to those specific to graphical shapes, presenting a methodology which can be used in a wide variety of applications. Additionally, readers are supplied with an insight into the problem of performance evaluation of spotting methods. Some very basic knowledge of pattern recognition, document image analysis and graphics recognition is assumed.

Topics and features:

  • Includes a Foreword by Professor Karl Tombre, Director of the INRIA Nancy - Grand Est research center and Editor-in-Chief of Springer’s International Journal on Document Analysis and Recognition
  • Introduces the problems of symbol spotting and focused retrieval, outlining an architecture for solving these problems
  • Examines techniques in computer vision for recognizing objects in scenes, and their application to the specific problem of spotting graphical symbols in documents
  • Describes a method to determine probable locations of symbols in technical drawings which makes use of vectorial signatures as symbol descriptors
  • Presents a spotting method which uses a prototype-based search as the basis for the focused retrieval task
  • Explores an indexing method that retrieves locations of interest where a query symbol is likely to be found
  • Investigates techniques for evaluating the performance of symbol-spotting systems, defined in terms of recognition abilities, location accuracy and scalability

Researchers and practitioners in the field of graphics recognition, interested in the problem of symbol spotting and focused retrieval applications in the context of digital libraries, will find this an invaluable text on the subject.

Dr. Marçal Rusiñol is a Research Associate at the Computer Vision Center and at the Computer Sciences Department of the Universitat Autònoma de Barcelona, Spain.

Dr. Josep Lladós is Director of the Computer Vision Center and Associate Professor at the Computer Sciences Department of the Universitat Autònoma de Barcelona, Spain.

Keywords

Focused Retrieval Graphical Pattern Indexation Graphics Recognition Performance Evaluation Symbol Description Symbol Spotting image analysis pattern recognition

Authors and affiliations

  • Marçal Rusiñol
    • 1
  • Josep Lladós
    • 2
  1. 1., Depto. Ciències de la ComputacióUniversitat Autònoma de BarcelonaBellaterraSpain
  2. 2.Depto. Ciències de la Computació, Centre de Visió per ComputadorUniversitat Autònoma de BarcelonaBellaterraSpain

Bibliographic information

  • DOI https://doi.org/10.1007/978-1-84996-208-7
  • Copyright Information Springer-Verlag London Limited 2010
  • Publisher Name Springer, London
  • eBook Packages Computer Science
  • Print ISBN 978-1-84996-207-0
  • Online ISBN 978-1-84996-208-7
  • About this book