11. Algorithms for Real-Time Object Detection in Images

  1. Amiya Nayak B.Math., Ph.D. Adjunct Research Professor Associate Editor Full Professor2 and
  2. Ivan Stojmenović Ph.D. Chair Professor founder editor-in-chief2,3
  1. Milos Stojmenovic

Published Online: 1 MAR 2007

DOI: 10.1002/9780470175668.ch11

Handbook of Applied Algorithms: Solving Scientific, Engineering and Practical Problems

Handbook of Applied Algorithms: Solving Scientific, Engineering and Practical Problems

How to Cite

Stojmenovic, M. (2008) Algorithms for Real-Time Object Detection in Images, in Handbook of Applied Algorithms: Solving Scientific, Engineering and Practical Problems (eds A. Nayak and I. Stojmenović), John Wiley & Sons, Inc., Hoboken, NJ, USA. doi: 10.1002/9780470175668.ch11

Editor Information

  1. 2

    SITE, University of Ottawa, 800 King Edward Ave., Ottawa, ON K1N 6N5, Canada

  2. 3

    EECE, University of Birmingham, UK

Author Information

  1. School of Information Technology and Engineering, University of Ottawa, Ottawa, ON K1N 6N5, Canada

Publication History

  1. Published Online: 1 MAR 2007
  2. Published Print: 14 FEB 2008

ISBN Information

Print ISBN: 9780470044926

Online ISBN: 9780470175668

SEARCH

Keywords:

  • real-time object detection algorithms in images;
  • cascaded decision process;
  • “bootstrap” strategy and face detection system

Summary

Real time face detection images has received growing attention recently. Recognition of other objects, such as cars, is also important. Applications are similar and content based real time image retrieval. Real time object detection in images is currently achieved by designing and applying automatic or semi-supervised machine learning algorithms. Some algorithmic solutions to these problems are reviewed. Existing real time object detection systems are based primarily on the AdaBoost framework, and the chapter will concentrate on it. Emphasis is given to approaches that build fast and reliable object recognizers in images based on small training sets. This is important in cases where the training set needs to be built manually, as in the case of detecting the back of cars, studied here as a particular example.