Applying two-pixel features to face detection

Nissenboim Ido, Keren Daniel, Michael Werman

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We propose a "quick rejection" paradigm which is applied to face detection. The features we use are arguably the simplest possible: a threshold on the difference between the grey levels of two pixels. No negative examples are used for training; instead, we use a simple statistical model of natural images. The resulting features are easy to find, extremely fast to apply, and achieve a good detection rate.

Original languageEnglish
Title of host publicationSITIS 2008 - Proceedings of the 4th International Conference on Signal Image Technology and Internet Based Systems
Pages65-69
Number of pages5
DOIs
StatePublished - 2008
Event4th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2008 - Bali, Indonesia
Duration: 30 Nov 20083 Dec 2008

Publication series

NameSITIS 2008 - Proceedings of the 4th International Conference on Signal Image Technology and Internet Based Systems

Conference

Conference4th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2008
Country/TerritoryIndonesia
CityBali
Period30/11/083/12/08

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software

Fingerprint

Dive into the research topics of 'Applying two-pixel features to face detection'. Together they form a unique fingerprint.

Cite this