Chapter 11. Algorithms for Real-Time Object Detection in Images
- Amiya Nayak B.Math., Ph.D. Adjunct Research Professor Associate Editor Full Professor2,
- Ivan Stojmenović Ph.D. Chair Professor founder editor-in-chief2,3
Published Online: 1 MAR 2007
DOI: 10.1002/9780470175668.ch11
Copyright © 2008 John Wiley & Sons, Inc.
Book Title
Handbook of Applied Algorithms: Solving Scientific, Engineering and Practical Problems
Additional Information
How to Cite
Stojmenovic, M. (2007) 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
- 2
SITE, University of Ottawa, 800 King Edward Ave., Ottawa, ON K1N 6N5, Canada
- 3
EECE, University of Birmingham, UK
Publication History
- Published Online: 1 MAR 2007
- Published Print: 14 FEB 2008
ISBN Information
Print ISBN: 9780470044926
Online ISBN: 9780470175668
- Summary
- Chapter
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.