Efficient face detection by a cascaded support–vector machine expansion

We describe a fast system for the detection and localization of human faces in images using a nonlinear 'support-vector machine'. We approximate the decision surface in terms of a reduced set of expansion vectors and propose a cascaded evaluation which has the property that the full suppor...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the Royal Society. A, Mathematical, physical, and engineering sciences Mathematical, physical, and engineering sciences, 2004-11, Vol.460 (2051), p.3283-3297
Main Authors: Romdhani, S., Torr, P., Schölkopf, B., Blake, A.
Format: Article
Language:English
Subjects:
Cascaded Evaluation
Classification
Coefficients
Computer pattern recognition
Computer vision
Face Detection
False negative errors
False positive errors
Image classification
Machine Learning
Mathematical vectors
Pixels
Rare Events Detection
Retraining
support-vector machines (SVMs)
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We describe a fast system for the detection and localization of human faces in images using a nonlinear 'support-vector machine'. We approximate the decision surface in terms of a reduced set of expansion vectors and propose a cascaded evaluation which has the property that the full support-vector expansion is only evaluated on the face-like parts of the image, while the largest part of typical images is classified using a single expansion vector (a simpler and more efficient classifier). As a result, only three reduced-set vectors are used, on average, to classify an image patch. Hence, the cascaded evaluation, presented in this paper, offers a thirtyfold speed-up over an evaluation using the full set of reduced-set vectors, which is itself already thirty times faster than classification using all the support vectors.
ISSN:1364-5021
1471-2946
DOI:10.1098/rspa.2004.1333