Show simple item record

dc.contributor.authorIscen, A.en_US
dc.contributor.authorGölge, E.en_US
dc.contributor.authorArmagan, A.en_US
dc.contributor.authorDuygulu P.en_US
dc.date.accessioned2016-02-08T12:07:58Z
dc.date.available2016-02-08T12:07:58Z
dc.date.issued2013en_US
dc.identifier.urihttp://hdl.handle.net/11693/28000
dc.description.abstractWe propose a method to recognize the scene of an image by finding the objects and the colors it contains. We approach this problem by creating a binary vector of detected objects and a histogram of the colors that the image contains. We then use these features to train a random forest classifier in order to determine the scene of each image. For class-based classifiers, our method gives comparable results with the state of art methods, such as Object Bank method, for the indoor scene dataset that we used. Additionally, while well-known methods are computationally expensive, our method has a low computational cost. © 2013 IEEE.en_US
dc.language.isoTurkishen_US
dc.source.title2013 21st Signal Processing and Communications Applications Conference, SIU 2013en_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/SIU.2013.6531220en_US
dc.subjectComputer visionen_US
dc.subjectPart based modelsen_US
dc.subjectRandom forestsen_US
dc.subjectScene recognitionen_US
dc.subjectColor distributionen_US
dc.subjectComputational costsen_US
dc.subjectPart-based modelsen_US
dc.subjectRandom forest classifieren_US
dc.subjectRandom forestsen_US
dc.subjectScene classificationen_US
dc.subjectScene recognitionen_US
dc.subjectState-of-art methodsen_US
dc.subjectColoren_US
dc.subjectComputer visionen_US
dc.subjectSignal processingen_US
dc.subjectDecision treesen_US
dc.titleScene classification with random forests and object and color distributionsen_US
dc.title.alternativeRastlantisal karar agaçlariyla nesne ve renk dagilimina göre sahne siniflandirilmasien_US
dc.typeConference Paperen_US
dc.departmentDepartment of Computer Engineering
dc.identifier.doi10.1109/SIU.2013.6531220en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record