Centre de documentation
scientifique

Sketch-Finder: efficient and effective sketch-based retrieval for large image collections / Carlos Alberto Pimentel Filho (August 2013)  

Public Titre : Sketch-Finder: efficient and effective sketch-based retrieval for large image collections Type de document : Article/Communication Auteurs : Carlos Alberto Pimentel Filho, Auteur ; Arnaldo de Albuquerque Araújo, Auteur ; Michel Crucianu, Auteur ; Valérie Gouet-Brunet , Auteur Editeur : Arequipa [Pérou] : Universidad Católica San Pablo UCSP Année de publication : August 2013 Conférence : SIBGRAPI 2013, 26th Brazilian Conference on Graphics, Patterns, and Images 05/08/2013 08/08/2013 Arequipa Pérou OA Proceedings Importance : pp 234 - 241 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] détection de contours [Termes IGN] indexation [Termes IGN] ondelette [Termes IGN] similitude [Termes IGN] variabilité Mots-clés libres : sketch-based image retrieval  multimedia indexing  scalability Résumé : (auteur) Among various image retrieval approaches, the use of sketches lets one express a precise visual query with simple and widespread means. The challenge consists in finding a content representation that allows you to effectively compare sketches and images, while supporting efficient retrieval in order to make the system scalable. We put forward a sketch-based image retrieval solution where sketches and natural image contours are represented and compared in the wavelet domain. The relevant information regarding query sketches and image content has, thus, a compact representation that can be readily employed by an efficient index for retrieval by similarity. Furthermore, with this solution, the balance between effectiveness and efficiency can be easily modified in order to adapt to the available resources. A comparative evaluation with a state-of-the-art method on the Paris dataset and a subset with 535K images of the ImageNet dataset shows that our solution can preserve effectiveness while being more than one order of magnitude faster. Numéro de notice : C2013-044 Affiliation des auteurs : LASTIG MATIS+Ext (2012-2019) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : sans En ligne : http://www.ucsp.edu.pe/sibgrapi2013/eproceedings/technical/114547_2.pdf Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80233