Notice: Undefined index: linkPowrot in C:\wwwroot\wwwroot\publikacje\publikacje.php on line 1275
[46740] Artykuł: Content Based Image Retrieval using Query by Approximate ShapeCzasopismo: Proceedings of the 2016 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS Tom: Vol. 8, Strony: 807-816ISSN: 2325-0348 ISBN: 978-8-3608-1090-3 Wydawca: IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA Opublikowano: Pażdziernik 2016 Seria wydawnicza: Federated Conference on Computer Science and Information Systems Liczba arkuszy wydawniczych: 1.00 Autorzy / Redaktorzy / Twórcy
Grupa MNiSW: Materiały z konferencji międzynarodowej (zarejestrowane w Web of Science) Punkty MNiSW: 15 Klasyfikacja Web of Science: Proceedings Paper Pełny tekst DOI Web of Science Słowa kluczowe: multimedialne bazy danych  wyszukiwanie szkicem  Keywords: multimedia databases  query by shape  query by sketch  |
In this paper we present a new method for content-based image retrieval. The method is based on querying database by approximate shape representing given object. In this way all images containing the object may be found. Shapes are specified as a set of geometric primitives and attributes. Relations between primitives are represented by a graph. Our graph matching algorithm is used for computing the level of similarity between shapes. The method may be also used for searching transformed as well as partially covered objects. Experimental results showed the efficiency of our approach.