Publication: A generative model for concurrent image retrieval and ROI segmentation
dc.affiliation.dpto | UC3M. Departamento de Teoría de la Señal y Comunicaciones | es |
dc.affiliation.grupoinv | UC3M. Grupo de Investigación: Procesado Multimedia | es |
dc.contributor.author | González Díaz, Iván | es |
dc.contributor.author | Baz-Hormigos, Carlos E. | es |
dc.contributor.author | Berdonces, Moisés | es |
dc.contributor.author | Díaz de María, Fernando | es |
dc.date.accessioned | 2015-09-18T09:26:06Z | |
dc.date.available | 2015-09-18T09:26:06Z | |
dc.date.issued | 2012 | |
dc.description | Proceedings of: 10th International Workshop on Content-Based Multimedia Indexing (CBMI). Annecy, France, 27-29 June 2012. | en |
dc.description.abstract | This paper proposes a probabilistic generative model that concurrently tackles the problems of image retrieval and detection of the region-of-interest (ROI). By introducing a latent variable that classifies the matches as true or false, we specifically focus on the application of geometric constrains to the keypoint matching process and the achievement of robust estimates of the geometric transformation between two images showing the same object. Our experiments in a challenging image retrieval database demonstrate that our approach outperforms the most prevalent approach for geometrically constrained matching, and compares favorably to other state-of-the-art methods. Furthermore, the proposed technique concurrently provides very good segmentations of the region of interest. | en |
dc.description.sponsorship | This work has been partially supported by the project AFICUS, co-funded by the Spanish Ministry of Industry, Trade and Tourism, and the European Fund for Regional Development, with Ref.: TSI-020110- 2009-103, and the National Grant TEC2011-26807 of the Spanish Ministry of Science and Innovation. | en |
dc.description.status | Publicado | es |
dc.format.extent | 6 | |
dc.format.mimetype | application/pdf | |
dc.identifier.bibliographicCitation | 2012 10th International Workshop pon Content- Based Multimedia Indexing (CBMI). (pp. 90-95). IEEE. | en |
dc.identifier.doi | 10.1109/CBMI.2012.6269844 | |
dc.identifier.isbn | 978-1-4673-2369-7 (online) | |
dc.identifier.isbn | 978-1-4673-2368-0 (print) | |
dc.identifier.issn | 1949-3983 | |
dc.identifier.publicationfirstpage | 90 | |
dc.identifier.publicationlastpage | 95 | |
dc.identifier.publicationtitle | 2012 10th International Workshop pon Content-Based Multimedia Indexing (CBMI) | en |
dc.identifier.uri | https://hdl.handle.net/10016/21584 | |
dc.identifier.uxxi | CC/0000017765 | |
dc.language.iso | eng | en |
dc.publisher | Ieee - The Institute Of Electrical And Electronics Engineers, Inc | en |
dc.relation.eventdate | 27-29 June 2012. | en |
dc.relation.eventnumber | 10 | |
dc.relation.eventplace | Annecy, France | en |
dc.relation.eventtitle | 10th International Workshop on Content-Based Multimedia Indexing (CBMI) | en |
dc.relation.projectID | Gobierno de España. TEC2011-26807 | es |
dc.relation.projectID | Gobierno de España. TSI-020110- 2009-103 | es |
dc.relation.publisherversion | http://dx.doi.org/10.1109/CBMI.2012.6269844 | |
dc.rights | © 2012 IEEE. | en |
dc.rights.accessRights | open access | en |
dc.subject.eciencia | Telecomunicaciones | es |
dc.subject.other | Image retrieval | en |
dc.subject.other | Image segmentation | en |
dc.title | A generative model for concurrent image retrieval and ROI segmentation | en |
dc.type | conference paper | * |
dc.type.hasVersion | AM | * |
dspace.entity.type | Publication |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- generative_CBMI_2012_ps.pdf
- Size:
- 1.18 MB
- Format:
- Adobe Portable Document Format