Scene classification with random forests and object and color distributions
Date
2013
Editor(s)
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
2013 21st Signal Processing and Communications Applications Conference (SIU)
Print ISSN
Electronic ISSN
Publisher
IEEE
Volume
Issue
Pages
Language
Turkish
Type
Journal Title
Journal ISSN
Volume Title
Series
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. © 2013 IEEE.
Course
Other identifiers
Book Title
Keywords
Computer vision , Part based models , Random forests , Scene recognition , Color distribution , Computational costs , Part-based models , Random forest classifier , Random forests , Scene classification , Scene recognition , State-of-art methods , Color , Computer vision , Signal processing , Decision trees