Face detection using classifiers cascade based on vector angle measure and multi-modal representation

F. Flitti, Amine Bermak

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper deals with face detection in still gray level images which is the first step in many automatic systems like video surveillance, face recognition, and images data base management. We propose a new face detection method using a classifiers cascade, each of which is based on a vector angle similarity measure between the investigated window and the face and nonface representatives (centroids). The latter are obtained using a clustering algorithm based on the same measure within the current training data sets, namely the low confidence classified samples at the previous stage of the cascade. First experiment results on refereed face data test sets are very satisfactory.

Original languageEnglish
Title of host publication2007 IEEE Workshop on Signal Processing Systems, SiPS 2007, Proceedings
Pages539-542
Number of pages4
DOIs
Publication statusPublished - 2007
Externally publishedYes
Event2007 IEEE Workshop on Signal Processing Systems, SiPS 2007 - Shanghai, China
Duration: 17 Oct 200719 Oct 2007

Other

Other2007 IEEE Workshop on Signal Processing Systems, SiPS 2007
CountryChina
CityShanghai
Period17/10/0719/10/07

Fingerprint

Face recognition
Classifiers
Clustering algorithms
Experiments

Keywords

  • Classifiers cascade
  • Face detection
  • Low confidence decision based training
  • Vector angle

ASJC Scopus subject areas

  • Media Technology
  • Signal Processing

Cite this

Flitti, F., & Bermak, A. (2007). Face detection using classifiers cascade based on vector angle measure and multi-modal representation. In 2007 IEEE Workshop on Signal Processing Systems, SiPS 2007, Proceedings (pp. 539-542). [4387605] https://doi.org/10.1109/SIPS.2007.4387605

Face detection using classifiers cascade based on vector angle measure and multi-modal representation. / Flitti, F.; Bermak, Amine.

2007 IEEE Workshop on Signal Processing Systems, SiPS 2007, Proceedings. 2007. p. 539-542 4387605.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Flitti, F & Bermak, A 2007, Face detection using classifiers cascade based on vector angle measure and multi-modal representation. in 2007 IEEE Workshop on Signal Processing Systems, SiPS 2007, Proceedings., 4387605, pp. 539-542, 2007 IEEE Workshop on Signal Processing Systems, SiPS 2007, Shanghai, China, 17/10/07. https://doi.org/10.1109/SIPS.2007.4387605
Flitti F, Bermak A. Face detection using classifiers cascade based on vector angle measure and multi-modal representation. In 2007 IEEE Workshop on Signal Processing Systems, SiPS 2007, Proceedings. 2007. p. 539-542. 4387605 https://doi.org/10.1109/SIPS.2007.4387605
Flitti, F. ; Bermak, Amine. / Face detection using classifiers cascade based on vector angle measure and multi-modal representation. 2007 IEEE Workshop on Signal Processing Systems, SiPS 2007, Proceedings. 2007. pp. 539-542
@inproceedings{eeed1ca9e3b74d548038644fd5b4f91c,
title = "Face detection using classifiers cascade based on vector angle measure and multi-modal representation",
abstract = "This paper deals with face detection in still gray level images which is the first step in many automatic systems like video surveillance, face recognition, and images data base management. We propose a new face detection method using a classifiers cascade, each of which is based on a vector angle similarity measure between the investigated window and the face and nonface representatives (centroids). The latter are obtained using a clustering algorithm based on the same measure within the current training data sets, namely the low confidence classified samples at the previous stage of the cascade. First experiment results on refereed face data test sets are very satisfactory.",
keywords = "Classifiers cascade, Face detection, Low confidence decision based training, Vector angle",
author = "F. Flitti and Amine Bermak",
year = "2007",
doi = "10.1109/SIPS.2007.4387605",
language = "English",
isbn = "1424412226",
pages = "539--542",
booktitle = "2007 IEEE Workshop on Signal Processing Systems, SiPS 2007, Proceedings",

}

TY - GEN

T1 - Face detection using classifiers cascade based on vector angle measure and multi-modal representation

AU - Flitti, F.

AU - Bermak, Amine

PY - 2007

Y1 - 2007

N2 - This paper deals with face detection in still gray level images which is the first step in many automatic systems like video surveillance, face recognition, and images data base management. We propose a new face detection method using a classifiers cascade, each of which is based on a vector angle similarity measure between the investigated window and the face and nonface representatives (centroids). The latter are obtained using a clustering algorithm based on the same measure within the current training data sets, namely the low confidence classified samples at the previous stage of the cascade. First experiment results on refereed face data test sets are very satisfactory.

AB - This paper deals with face detection in still gray level images which is the first step in many automatic systems like video surveillance, face recognition, and images data base management. We propose a new face detection method using a classifiers cascade, each of which is based on a vector angle similarity measure between the investigated window and the face and nonface representatives (centroids). The latter are obtained using a clustering algorithm based on the same measure within the current training data sets, namely the low confidence classified samples at the previous stage of the cascade. First experiment results on refereed face data test sets are very satisfactory.

KW - Classifiers cascade

KW - Face detection

KW - Low confidence decision based training

KW - Vector angle

UR - http://www.scopus.com/inward/record.url?scp=47949119734&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47949119734&partnerID=8YFLogxK

U2 - 10.1109/SIPS.2007.4387605

DO - 10.1109/SIPS.2007.4387605

M3 - Conference contribution

AN - SCOPUS:47949119734

SN - 1424412226

SN - 9781424412228

SP - 539

EP - 542

BT - 2007 IEEE Workshop on Signal Processing Systems, SiPS 2007, Proceedings

ER -