Show simple item record

Error weighted classifier combination for multi-modal human identification

dc.date.accessioned2005-12-22T02:44:17Z
dc.date.accessioned2018-11-24T10:24:41Z
dc.date.available2005-12-22T02:44:17Z
dc.date.available2018-11-24T10:24:41Z
dc.date.issued2005-12-14
dc.identifier.urihttp://hdl.handle.net/1721.1/30590
dc.identifier.urihttp://repository.aust.edu.ng/xmlui/handle/1721.1/30590
dc.description.abstractIn this paper we describe a technique of classifier combination used in a human identification system. The system integrates all available features from multi-modal sources within a Bayesian framework. The framework allows representinga class of popular classifier combination rules and methods within a single formalism. It relies on a  per-class measure of confidence derived from performance of each classifier on training data that is shown to improve performance on a synthetic data set. The method is especially relevant in autonomous surveillance setting where varying time scales and missing features are a common occurrence. We show an application of this technique to the real-world surveillance database of video and audio recordings of people collected over several weeks in the office setting.
dc.format.extent7 p.
dc.format.extent22108540 bytes
dc.format.extent952178 bytes
dc.language.isoen_US
dc.subjectAI
dc.subjectclassifier combination
dc.subjectface recognition
dc.subjectidentification
dc.subjectmulti-modal
dc.titleError weighted classifier combination for multi-modal human identification


Files in this item

FilesSizeFormatView
MIT-CSAIL-TR-2005-080.pdf952.1Kbapplication/pdfView/Open
MIT-CSAIL-TR-2005-080.ps22.10Mbapplication/postscriptView/Open

This item appears in the following Collection(s)

Show simple item record