Show simple item record

dc.contributor.authorNakajima, Chikahitoen_US
dc.contributor.authorPontil, Massimilianoen_US
dc.contributor.authorHeisele, Bernden_US
dc.contributor.authorPoggio, Tomasoen_US
dc.date.accessioned2004-10-20T21:03:31Z
dc.date.available2004-10-20T21:03:31Z
dc.date.issued2000-06-01en_US
dc.identifier.otherAIM-1688en_US
dc.identifier.otherCBCL-188en_US
dc.identifier.urihttp://hdl.handle.net/1721.1/7230
dc.description.abstractWe describe a system that learns from examples to recognize people in images taken indoors. Images of people are represented by color-based and shape-based features. Recognition is carried out through combinations of Support Vector Machine classifiers (SVMs). Different types of multiclass strategies based on SVMs are explored and compared to k-Nearest Neighbors classifiers (kNNs). The system works in real time and shows high performance rates for people recognition throughout one day.en_US
dc.format.extent4611797 bytes
dc.format.extent373760 bytes
dc.format.mimetypeapplication/postscript
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.relation.ispartofseriesAIM-1688en_US
dc.relation.ispartofseriesCBCL-188en_US
dc.titlePeople Recognition in Image Sequences by Supervised Learningen_US


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record