Skip to main navigation Skip to search Skip to main content

Rastlantisal karar agaçlariyla nesne ve renk dagilimina göre sahne siniflandirilmasi

Translated title of the contribution: Scene classification with random forests and object and color distributions
  • Bilkent University

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

1 Citation (Scopus)

Abstract

We 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.

Translated title of the contributionScene classification with random forests and object and color distributions
Original languageTurkish
Title of host publication2013 21st Signal Processing and Communications Applications Conference, SIU 2013
DOIs
Publication statusPublished - 2013
Externally publishedYes
Event2013 21st Signal Processing and Communications Applications Conference, SIU 2013 - Haspolat, Turkey
Duration: 24 Apr 201326 Apr 2013

Publication series

Name2013 21st Signal Processing and Communications Applications Conference, SIU 2013

Conference

Conference2013 21st Signal Processing and Communications Applications Conference, SIU 2013
Country/TerritoryTurkey
CityHaspolat
Period24/04/1326/04/13

Fingerprint

Dive into the research topics of 'Scene classification with random forests and object and color distributions'. Together they form a unique fingerprint.

Cite this