Please use this identifier to cite or link to this item: https://doi.org/10.1142/S0218001412550014
Title: New edge characteristics for scene and object classification
Authors: Shivakumara, P. 
Rajan, D.
Sadananthan, S.A.
Keywords: Caltech object classification
Edge properties
scene category
voting
Issue Date: 2012
Citation: Shivakumara, P., Rajan, D., Sadananthan, S.A. (2012). New edge characteristics for scene and object classification. International Journal of Pattern Recognition and Artificial Intelligence 26 (1). ScholarBank@NUS Repository. https://doi.org/10.1142/S0218001412550014
Abstract: In this paper, we show that simple edge characteristics in images, when judiciously combined, can result in improved scene and object classification. Unlike existing methods that require a large number of training samples and complex learning schemes, our method discovers simple edge properties. We introduce three sets of edge properties, namely, centroid, compactness and aspect ratio of edges in the image. The combinations of these edge properties are used to discriminate among images in each class. A class representative is calculated for each class according to the average percentage of edges that satisfy the property of a particular class. This percentage for an unknown image is compared to the class representative to assign a label to it. It is shown that this simple edge properties-based method outperforms some of the state-of-the-art results on scene and object classification on standard databases. © 2012 World Scientific Publishing Company.
Source Title: International Journal of Pattern Recognition and Artificial Intelligence
URI: http://scholarbank.nus.edu.sg/handle/10635/39051
ISSN: 02180014
DOI: 10.1142/S0218001412550014
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

2
checked on Oct 10, 2018

WEB OF SCIENCETM
Citations

1
checked on Oct 10, 2018

Page view(s)

58
checked on Oct 13, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.