Skip to main content

Advertisement

SpringerLink
Log in
Menu
Find a journal Publish with us
Search
Cart
Book cover

Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR)

SSPR /SPR 2012: Structural, Syntactic, and Statistical Pattern Recognition pp 31–32Cite as

  1. Home
  2. Structural, Syntactic, and Statistical Pattern Recognition
  3. Conference paper
Hierarchical Compositional Representations of Object Structure

Hierarchical Compositional Representations of Object Structure

  • Aleš Leonardis24,25 
  • Conference paper
  • 2326 Accesses

Part of the Lecture Notes in Computer Science book series (LNIP,volume 7626)

Abstract

Visual categorisation has been an area of intensive research in the vision community for several decades. Ultimately, the goal is to efficiently detect and recognize an increasing number of object classes. The problem entangles three highly interconnected issues: the internal object representation, which should compactly capture the visual variability of objects and generalize well over each class; a means for learning the representation from a set of input images with as little supervision as possible; and an effective inference algorithm that robustly matches the object representation against the image and scales favorably with the number of objects.

In this talk I will present our approach which combines a learned compositional hierarchy, representing (2D) shapes of multiple object classes, and a coarse-to-fine matching scheme that exploits a taxonomy of objects to perform efficient object detection. Our framework for learning a hierarchical compositional shape vocabulary for representing multiple object classes takes simple contour fragments and learns their frequent spatial configurations. These are recursively combined into increasingly more complex and class-specific shape compositions, each exerting a high degree of shape variability. At the top-level of the vocabulary, the compositions represent the whole shapes of the objects. The vocabulary is learned layer after layer, by gradually increasing the size of the window of analysis and reducing the spatial resolution at which the shape configurations are learned. The lower layers are learned jointly on images of all classes, whereas the higher layers of the vocabulary are learned incrementally, by presenting the algorithm with one object class after another.

However, in order for recognition systems to scale to a larger number of object categories, and achieve running times logarithmic in the number of classes, building visual class taxonomies becomes necessary. We propose an approach for speeding up recognition times of multi-class part-based object representations. The main idea is to construct a taxonomy of constellation models cascaded from coarse-to-fine resolution and use it in recognition with an efficient search strategy. The structure and the depth of the taxonomy is built automatically in a way that minimizes the number of expected computations during recognition by optimizing the cost-to-power ratio. The combination of the learned taxonomy with the compositional hierarchy of object shape achieves efficiency both with respect to the representation of the structure of objects and in terms of the number of modeled object classes. The experimental results show that the learned multi-class object representation achieves a detection performance comparable to the current state-of-the-art flat approaches with both faster inference and shorter training times.

Download conference paper PDF

Author information

Authors and Affiliations

  1. Visual Cognitive Systems Laboratory, Faculty of Computer and Information Science, University of Ljubljana, Tržaška 25, SI-1001, Ljubljana, Slovenia

    Aleš Leonardis

  2. School of Computer Science, University of Birmingham, Edgbaston, Birmingham, B15 2TT, United Kingdom

    Aleš Leonardis

Authors
  1. Aleš Leonardis
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Computer Science, University of Auckland, Private Bag 92019, 1142, Auckland, New Zealand

    Georgy Gimel’farb

  2. Department of Computer Science, University of York, Deramore Lane, YO10 5GH, York, UK

    Edwin Hancock

  3. Institute of Media and Information Technology, Chiba University, Yayoi-cho 1-33, 263-8522, Inage-ku, Chiba, Japan

    Atsushi Imiya

  4. Technische Universität/Fraunhofer IGD, Fraunhoferstraße 5, 64283, Darmstadt, Germany

    Arjan Kuijper

  5. Graduate School of Information Science and Technology, Hokkaido University, 060-0814, Sapporo, Japan

    Mineichi Kudo

  6. Graduate School of Engineering, Tohoku University, 6-6-05 Aoba, Aramaki, Aoba-ku, 980-8579, Sendai, Miyagi, Japan

    Shinichiro Omachi

  7. Centre for Vision, Speech and Signal Processing, University of Surrey, GU2 7XH, Guildford, Surrey, UK

    Terry Windeatt

  8. C&C Innovation Research Laboratories, NEC Corporation, 8916-47 Takayama-cho, Ikoma-Shi, Nara, Japan

    Keiji Yamada

Rights and permissions

Reprints and Permissions

Copyright information

© 2012 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Leonardis, A. (2012). Hierarchical Compositional Representations of Object Structure. In: Gimel’farb, G., et al. Structural, Syntactic, and Statistical Pattern Recognition. SSPR /SPR 2012. Lecture Notes in Computer Science, vol 7626. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34166-3_3

Download citation

  • .RIS
  • .ENW
  • .BIB
  • DOI: https://doi.org/10.1007/978-3-642-34166-3_3

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-34165-6

  • Online ISBN: 978-3-642-34166-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Share this paper

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

  • The International Association for Pattern Recognition

    Published in cooperation with

    http://www.iapr.org/

Search

Navigation

  • Find a journal
  • Publish with us

Discover content

  • Journals A-Z
  • Books A-Z

Publish with us

  • Publish your research
  • Open access publishing

Products and services

  • Our products
  • Librarians
  • Societies
  • Partners and advertisers

Our imprints

  • Springer
  • Nature Portfolio
  • BMC
  • Palgrave Macmillan
  • Apress
  • Your US state privacy rights
  • Accessibility statement
  • Terms and conditions
  • Privacy policy
  • Help and support

167.114.118.210

Not affiliated

Springer Nature

© 2023 Springer Nature