New edge charasteristics for scene and object classification
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...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2013
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/101881 http://hdl.handle.net/10220/16904 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-101881 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1018812020-05-28T07:18:18Z New edge charasteristics for scene and object classification Shivakumara, Palaiahnakote Rajan, Deepu Sadananthan, Suresh Anand School of Computer Engineering DRNTU::Engineering::Computer science and engineering 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. 2013-10-25T03:31:14Z 2019-12-06T20:46:14Z 2013-10-25T03:31:14Z 2019-12-06T20:46:14Z 2012 2012 Journal Article Shivakumara, P., Rajan, D., & Sadananthan, S. A. (2012). New Edge Charasteristics For Scene And Object Classification. International Journal of Pattern Recognition and Artificial Intelligence, 26(01), 1255001. https://hdl.handle.net/10356/101881 http://hdl.handle.net/10220/16904 10.1142/S0218001412550014 en International journal of pattern recognition and artificial intelligence |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
DRNTU::Engineering::Computer science and engineering |
spellingShingle |
DRNTU::Engineering::Computer science and engineering Shivakumara, Palaiahnakote Rajan, Deepu Sadananthan, Suresh Anand New edge charasteristics for scene and object classification |
description |
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. |
author2 |
School of Computer Engineering |
author_facet |
School of Computer Engineering Shivakumara, Palaiahnakote Rajan, Deepu Sadananthan, Suresh Anand |
format |
Article |
author |
Shivakumara, Palaiahnakote Rajan, Deepu Sadananthan, Suresh Anand |
author_sort |
Shivakumara, Palaiahnakote |
title |
New edge charasteristics for scene and object classification |
title_short |
New edge charasteristics for scene and object classification |
title_full |
New edge charasteristics for scene and object classification |
title_fullStr |
New edge charasteristics for scene and object classification |
title_full_unstemmed |
New edge charasteristics for scene and object classification |
title_sort |
new edge charasteristics for scene and object classification |
publishDate |
2013 |
url |
https://hdl.handle.net/10356/101881 http://hdl.handle.net/10220/16904 |
_version_ |
1681057307832614912 |