Show simple item record

dc.contributorThe Pennsylvania State University CiteSeerX Archives
dc.contributor.authorBruce Draper Jose
dc.contributor.authorJose Bins
dc.contributor.authorKyungim Baek
dc.date.accessioned2019-10-24T03:45:12Z
dc.date.available2019-10-24T03:45:12Z
dc.date.created2017-01-05 00:47
dc.date.issued2009-04-15
dc.identifieroai:CiteSeerX.psu:10.1.1.20.9830
dc.identifierhttp://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.9830
dc.identifier.urihttp://hdl.handle.net/20.500.12424/818926
dc.description.abstract. Many modern computer vision systems are built by chaining together standard vision procedures, often in graphical programming environments such as Khoros, CVIPtools or IUE. Typically, these procedures are selected and sequenced by an ad-hoc combination of programmer's intuition and trial-and-error. This paper presents a theoretically sound method for constructing object recognition strategies by casting object recognition as a Markov Decision Problem (MDP). The result is a system called ADORE (Adaptive Object Recognition) that automatically learns object recognition control policies from training data. Experimental results are presented in which ADORE is trained to recognize five types of houses in aerial images, and where its performance can be (and is) compared to optimal. 1
dc.format.mediumapplication/pdf
dc.languageen
dc.language.isoeng
dc.rightsMetadata may be used without restrictions as long as the oai identifier remains attached to it.
dc.titleADORE: Adaptive Object Recognition
dc.typetext
ge.collectioncodeOAIDATA
ge.dataimportlabelOAI metadata object
ge.identifier.legacyglobethics:10414717
ge.identifier.permalinkhttps://www.globethics.net/gel/10414717
ge.lastmodificationdate2017-01-05 00:47
ge.lastmodificationuseradmin@pointsoftware.ch (import)
ge.submissions0
ge.oai.exportid148934
ge.oai.repositoryid54
ge.oai.streamid2
ge.setnameGlobeEthicsLib
ge.setspecglobeethicslib
ge.linkhttp://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.20.9830
ge.linkhttp://www.cs.colostate.edu/~draper/publications/draper_icvs99.pdf


This item appears in the following Collection(s)

Show simple item record