Real-time face detection using a cascade of neural network ensembles

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

Abstract

We propose a (neat) real-time face del.ect.or using a cascade of parallel neuTal net.work: (NN) ensembles for enhanced detection aCCUTacy and efficiency. First, we fon7/. a coordinated NN ensemble by sequentially tmining a set of neuml netw01ks with the same topology. The I.mining implicitly paTtitions the face space into a nurnbeT of di.~joint n:gions, and each NN 'is specialized in a spec~fic S11,b-l·egion. Second, to reduce the /.otal comp'lttal.ion cost for t.he face det.ect.ion, a series of NN ensembles aTe cascaded s1tch thai. the complexity of base nel:w01'ks increases. Our pTOJlosed apJlTOach achieves 1/,P to 94 % detection Tate (CM U + MIT test set) and 3-4 % frames/sec. det.ect.ion speed on a nan7/.al PC (P-IV, 3.0GHz).
Original languageEnglish
Title of host publication26th Symposium on Information Theory in the Benelux
EditorsN. Cerf, O. Delgrange, J. Cardinal
Place of PublicationBrussels
PublisherWerkgemeenschap voor Informatie- en Communicatietheorie (WIC)
Pages47-54
ISBN (Print)90-71048-21-7
Publication statusPublished - 2005
Event2005 Symposium on Information Theory in the Benelux (SITB 2005) - Brussels, Belgium
Duration: 19 May 200520 May 2005
Conference number: 26

Conference

Conference2005 Symposium on Information Theory in the Benelux (SITB 2005)
Country/TerritoryBelgium
CityBrussels
Period19/05/0520/05/05

Fingerprint

Dive into the research topics of 'Real-time face detection using a cascade of neural network ensembles'. Together they form a unique fingerprint.

Cite this