Advertisement

© 2016

Knowledge Transfer between Computer Vision and Text Mining

Similarity-based Learning Approaches

Benefits

  • Provides a novel perspective on image analysis and text processing, presenting the scientific justification for treating the two disciplines in a similar manner

  • Offers open source code for the techniques in the book at an associated website

  • Reviews state-of-the-art similarity-based learning approaches, including nearest neighbor models, kernel methods and clustering algorithms

Book

Part of the Advances in Computer Vision and Pattern Recognition book series (ACVPR)

Table of contents

  1. Front Matter
    Pages i-xxiv
  2. Radu Tudor Ionescu, Marius Popescu
    Pages 1-13
  3. Radu Tudor Ionescu, Marius Popescu
    Pages 15-37
  4. Knowledge Transfer from Text Mining to Computer Vision

    1. Front Matter
      Pages 39-39
    2. Radu Tudor Ionescu, Marius Popescu
      Pages 41-52
    3. Radu Tudor Ionescu, Marius Popescu
      Pages 53-98
    4. Radu Tudor Ionescu, Marius Popescu
      Pages 99-132
  5. Knowledge Transfer from Computer Vision to Text Mining

    1. Front Matter
      Pages 133-133
    2. Radu Tudor Ionescu, Marius Popescu
      Pages 135-147
    3. Radu Tudor Ionescu, Marius Popescu
      Pages 149-191
    4. Radu Tudor Ionescu, Marius Popescu
      Pages 193-227
    5. Radu Tudor Ionescu, Marius Popescu
      Pages 229-241
    6. Radu Tudor Ionescu, Marius Popescu
      Pages 243-246
  6. Back Matter
    Pages 247-250

About this book

Introduction

This ground-breaking text/reference diverges from the traditional view that computer vision (for image analysis) and string processing (for text mining) are separate and unrelated fields of study, propounding that images and text can be treated in a similar manner for the purposes of information retrieval, extraction and classification. Highlighting the benefits of knowledge transfer between the two disciplines, the text presents a range of novel similarity-based learning techniques founded on this approach.

Topics and features:

  • Describes a variety of similarity-based learning approaches, including nearest neighbor models, local learning, kernel methods, and clustering algorithms
  • Presents a nearest neighbor model based on a novel dissimilarity for images, and applies this for handwritten digit recognition and texture analysis
  • Discusses a novel kernel for (visual) word histograms, as well as several kernels based on pyramid representation, and uses these for facial expression recognition and text categorization by topic
  • Introduces an approach based on string kernels for native language identification
  • Contains links for downloading relevant open source code
  • With a foreword by Prof. Florentina Hristea

This unique work will be of great benefit to researchers, postgraduate and advanced undergraduate students involved in machine learning, data science, text mining and computer vision.

Dr. Radu Tudor Ionescu is an Assistant Professor in the Department of Computer Science at the University of Bucharest, Romania. Dr. Marius Popescu is an Associate Professor at the same institution.

Keywords

Computer Vision Kernel Methods Knowledge Transfer Similarity-based Learning Text Mining

Authors and affiliations

  1. 1.Faculty of Math. and Computer ScienceUniversity of BucharestBucharestRomania
  2. 2.Department of Computer ScienceUniversity of BucharestBucharestRomania

About the authors

Dr. Radu Tudor Ionescu is an Assistant Professor in the Department of Computer Science at the University of Bucharest, Romania.

Dr. Marius Popescu is an Associate Professor at the same institution.

Bibliographic information

  • Book Title Knowledge Transfer between Computer Vision and Text Mining
  • Book Subtitle Similarity-based Learning Approaches
  • Authors Radu Tudor Ionescu
    Marius Popescu
  • Series Title Advances in Computer Vision and Pattern Recognition
  • Series Abbreviated Title Advs Comp. Vision, Pattern Recognition
  • DOI https://doi.org/10.1007/978-3-319-30367-3
  • Copyright Information Springer International Publishing Switzerland 2016
  • Publisher Name Springer, Cham
  • eBook Packages Computer Science Computer Science (R0)
  • Hardcover ISBN 978-3-319-30365-9
  • Softcover ISBN 978-3-319-80791-1
  • eBook ISBN 978-3-319-30367-3
  • Series ISSN 2191-6586
  • Series E-ISSN 2191-6594
  • Edition Number 1
  • Number of Pages XXIV, 250
  • Number of Illustrations 9 b/w illustrations, 33 illustrations in colour
  • Topics Artificial Intelligence
    Image Processing and Computer Vision
    Data Mining and Knowledge Discovery
  • Buy this book on publisher's site
Industry Sectors
Automotive
Chemical Manufacturing
Biotechnology
IT & Software
Telecommunications
Law
Consumer Packaged Goods
Pharma
Materials & Steel
Finance, Business & Banking
Electronics
Energy, Utilities & Environment
Aerospace
Oil, Gas & Geosciences
Engineering