| dc.contributor.author |
Heisele, Bernd |
en_US |
| dc.contributor.author |
Poggio, Tomaso |
en_US |
| dc.contributor.author |
Pontil, Massimiliano |
en_US |
| dc.date.accessioned |
2004-10-20T21:03:29Z |
|
| dc.date.available |
2004-10-20T21:03:29Z |
|
| dc.date.issued |
2000-05-01 |
en_US |
| dc.identifier.other |
AIM-1687 |
en_US |
| dc.identifier.other |
CBCL-187 |
en_US |
| dc.identifier.uri |
http://hdl.handle.net/1721.1/7229 |
|
| dc.description.abstract |
We present a trainable system for detecting frontal and near-frontal views of faces in still gray images using Support Vector Machines (SVMs). We first consider the problem of detecting the whole face pattern by a single SVM classifer. In this context we compare different types of image features, present and evaluate a new method for reducing the number of features and discuss practical issues concerning the parameterization of SVMs and the selection of training data. The second part of the paper describes a component-based method for face detection consisting of a two-level hierarchy of SVM classifers. On the first level, component classifers independently detect components of a face, such as the eyes, the nose, and the mouth. On the second level, a single classifer checks if the geometrical configuration of the detected components in the image matches a geometrical model of a face. |
en_US |
| dc.description.provenance |
Made available in DSpace on 2004-10-20T21:03:29Z (GMT). No. of bitstreams: 2
AIM-1687.ps: 6267853 bytes, checksum: 53d05a0d6dc3879ca5109297e31ff3c9 (MD5)
AIM-1687.pdf: 482304 bytes, checksum: 11fd4fd18edb448320f69eb12c1b8435 (MD5)
Previous issue date: 2000-05-01 |
en |
| dc.format.extent |
6267853 bytes |
|
| dc.format.extent |
482304 bytes |
|
| dc.format.mimetype |
application/postscript |
|
| dc.format.mimetype |
application/pdf |
|
| dc.language.iso |
en_US |
|
| dc.relation.ispartofseries |
AIM-1687 |
en_US |
| dc.relation.ispartofseries |
CBCL-187 |
en_US |
| dc.title |
Face Detection in Still Gray Images |
en_US |
