File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.patcog.2009.11.009
- Scopus: eid_2-s2.0-75749158448
- WOS: WOS:000275615800013
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Scene categorization via contextual visual words
Title | Scene categorization via contextual visual words |
---|---|
Authors | |
Keywords | Context based vision Contextual visual words Pattern recognition Scene categorization |
Issue Date | 2010 |
Publisher | Elsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pr |
Citation | Pattern Recognition, 2010, v. 43 n. 5, p. 1874-1888 How to Cite? |
Abstract | In this paper, we propose a novel scene categorization method based on contextual visual words. In the proposed method, we extend the traditional 'bags of visual words' model by introducing contextual information from the coarser scale and neighborhood regions to the local region of interest based on unsupervised learning. The introduced contextual information provides useful information or cue about the region of interest, which can reduce the ambiguity when employing visual words to represent the local regions. The improved visual words representation of the scene image is capable of enhancing the categorization performance. The proposed method is evaluated over three scene classification datasets, with 8, 13 and 15 scene categories, respectively, using 10-fold cross-validation. The experimental results show that the proposed method achieves 90.30%, 87.63% and 85.16% recognition success for Dataset 1, 2 and 3, respectively, which significantly outperforms the methods based on the visual words that only represent the local information in the statistical manner. We also compared the proposed method with three representative scene categorization methods. The result confirms the superiority of the proposed method. © 2009 Elsevier Ltd. All rights reserved. |
Persistent Identifier | http://hdl.handle.net/10722/124677 |
ISSN | 2023 Impact Factor: 7.5 2023 SCImago Journal Rankings: 2.732 |
ISI Accession Number ID | |
References |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Qin, J | en_HK |
dc.contributor.author | Yung, NHC | en_HK |
dc.date.accessioned | 2010-10-31T10:47:59Z | - |
dc.date.available | 2010-10-31T10:47:59Z | - |
dc.date.issued | 2010 | en_HK |
dc.identifier.citation | Pattern Recognition, 2010, v. 43 n. 5, p. 1874-1888 | en_HK |
dc.identifier.issn | 0031-3203 | en_HK |
dc.identifier.uri | http://hdl.handle.net/10722/124677 | - |
dc.description.abstract | In this paper, we propose a novel scene categorization method based on contextual visual words. In the proposed method, we extend the traditional 'bags of visual words' model by introducing contextual information from the coarser scale and neighborhood regions to the local region of interest based on unsupervised learning. The introduced contextual information provides useful information or cue about the region of interest, which can reduce the ambiguity when employing visual words to represent the local regions. The improved visual words representation of the scene image is capable of enhancing the categorization performance. The proposed method is evaluated over three scene classification datasets, with 8, 13 and 15 scene categories, respectively, using 10-fold cross-validation. The experimental results show that the proposed method achieves 90.30%, 87.63% and 85.16% recognition success for Dataset 1, 2 and 3, respectively, which significantly outperforms the methods based on the visual words that only represent the local information in the statistical manner. We also compared the proposed method with three representative scene categorization methods. The result confirms the superiority of the proposed method. © 2009 Elsevier Ltd. All rights reserved. | en_HK |
dc.language | eng | en_HK |
dc.publisher | Elsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pr | en_HK |
dc.relation.ispartof | Pattern Recognition | en_HK |
dc.subject | Context based vision | en_HK |
dc.subject | Contextual visual words | en_HK |
dc.subject | Pattern recognition | en_HK |
dc.subject | Scene categorization | en_HK |
dc.title | Scene categorization via contextual visual words | en_HK |
dc.type | Article | en_HK |
dc.identifier.openurl | http://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0031-3203&volume=43&spage=1874 &epage= 1888&date=2010&atitle=Scene+categorization+via+contextual+visual+words | en_HK |
dc.identifier.email | Yung, NHC:nyung@eee.hku.hk | en_HK |
dc.identifier.authority | Yung, NHC=rp00226 | en_HK |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.patcog.2009.11.009 | en_HK |
dc.identifier.scopus | eid_2-s2.0-75749158448 | en_HK |
dc.identifier.hkuros | 176242 | en_HK |
dc.relation.references | http://www.scopus.com/mlt/select.url?eid=2-s2.0-75749158448&selection=ref&src=s&origin=recordpage | en_HK |
dc.identifier.volume | 43 | en_HK |
dc.identifier.issue | 5 | en_HK |
dc.identifier.spage | 1874 | en_HK |
dc.identifier.epage | 1888 | en_HK |
dc.identifier.eissn | 1873-5142 | - |
dc.identifier.isi | WOS:000275615800013 | - |
dc.publisher.place | Netherlands | en_HK |
dc.identifier.scopusauthorid | Qin, J=24450951900 | en_HK |
dc.identifier.scopusauthorid | Yung, NHC=7003473369 | en_HK |
dc.identifier.citeulike | 6408606 | - |
dc.identifier.issnl | 0031-3203 | - |