File(s) under permanent embargo
Empirical study of multi-label classification methods for image annotation and retrieval
conference contribution
posted on 2010-01-01, 00:00 authored by Gulisong NasierdingGulisong Nasierding, Abbas KouzaniAbbas KouzaniThis paper presents an empirical study of multi-label classification methods, and gives suggestions for multi-label classification that are effective for automatic image annotation applications. The study shows that triple random ensemble multi-label classification algorithm (TREMLC) outperforms among its counterparts, especially on scene image dataset. Multi-label k-nearest neighbor (ML-kNN) and binary relevance (BR) learning algorithms perform well on Corel image dataset. Based on the overall evaluation results, examples are given to show label prediction performance for the algorithms using selected image examples. This provides an indication of the suitability of different multi-label classification methods for automatic image annotation under different problem settings.
History
Event
Digital Image Computing : Techniques and Application Conference (2010 : Sydney, N.S.W.)Pagination
617 - 622Publisher
DICTALocation
Sydney, NSWPlace of publication
Sydney, NSWStart date
2010-12-01End date
2010-12-03ISBN-13
9781424488162Language
engPublication classification
E1 Full written paper - refereedCopyright notice
2010, IEEETitle of proceedings
DICTA 2010 : Proceedings of the Digital Image Computing : Techniques and ApplicationUsage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC