Browse wiki

Object recognition in wikimage data based on local invariant image features
Abstract Object recognition is an essential task inObject recognition is an essential task in content-based image retrieval and classification. This paper deals with object recognition in WIKImage data, a collection of publicly available annotated Wikipedia images. WIKImage comprises a set of 14 binary classification problems with significant class imbalance. Our approach is based on using the local invariant image features and we have compared 3 standard and widely used feature types: SIFT, SURF and ORB. We have examined how the choice of representation affects the k-nearest neighbor data topology and have shown that some feature types might be more appropriate than others for this particular problem. In order to assess the difficulty of the data, we have evaluated 7 different k-nearest neighbor classification methods and shown that the recently proposed hubness-aware classifiers might be used to either increase the accuracy of prediction, or the macro-averaged F-score. However, our results indicate that further improvements are possible and that including the textual feature information might prove beneficial for system performance.t prove beneficial for system performance.
Abstractsub Object recognition is an essential task inObject recognition is an essential task in content-based image retrieval and classification. This paper deals with object recognition in WIKImage data, a collection of publicly available annotated Wikipedia images. WIKImage comprises a set of 14 binary classification problems with significant class imbalance. Our approach is based on using the local invariant image features and we have compared 3 standard and widely used feature types: SIFT, SURF and ORB. We have examined how the choice of representation affects the k-nearest neighbor data topology and have shown that some feature types might be more appropriate than others for this particular problem. In order to assess the difficulty of the data, we have evaluated 7 different k-nearest neighbor classification methods and shown that the recently proposed hubness-aware classifiers might be used to either increase the accuracy of prediction, or the macro-averaged F-score. However, our results indicate that further improvements are possible and that including the textual feature information might prove beneficial for system performance.t prove beneficial for system performance.
Bibtextype inproceedings  +
Doi 10.1109/ICCP.2013.6646097  +
Has author Tomasev N. + , Pracner D. + , Brehar R. + , Radovanovic M. + , Mladenic D. + , Ivanovic M. + , Nedevschi S. +
Has extra keyword Hubness + , Image + , Local invariant features + , WIKImage + , Wikipedia + , Classification (of information) + , Communication + , Content based retrieval + , Topology + , Object recognition +
Has keyword Classification + , Hubness + , Image + , Local invariant features + , Object recognition + , WIKImage + , Wikipedia +
Isbn 9781479914937  +
Language English +
Number of citations by publication 0  +
Number of references by publication 0  +
Pages 139–146  +
Published in Proceedings - 2013 IEEE 9th International Conference on Intelligent Computer Communication and Processing, ICCP 2013 +
Title Object recognition in wikimage data based on local invariant image features +
Type conference paper  +
Year 2013 +
Creation dateThis property is a special property in this wiki. 6 November 2014 15:29:47  +
Categories Publications without license parameter  + , Publications without remote mirror parameter  + , Publications without archive mirror parameter  + , Publications without paywall mirror parameter  + , Conference papers  + , Publications without references parameter  + , Publications  +
Modification dateThis property is a special property in this wiki. 6 November 2014 15:29:47  +
DateThis property is a special property in this wiki. 2013  +
hide properties that link here 
Object recognition in wikimage data based on local invariant image features + Title
 

 

Enter the name of the page to start browsing from.