Utilization of interest point detectors in content based image retrieval

Autor: Zukal, Martin, Číka, Petr
Přispěvatelé: Pihera, Josef, Steiner, František
Jazyk: angličtina
Rok vydání: 2011
Předmět:
Popis: The paper deals with content based image retrieval in general and interest point detectors as one of possible methods used in object recognition. There are described current trends in narrowing down the so called “Semantic gap” and we propose a new solution how to achieve it. Furthermore, we evaluate three common interest point detectors with respect to the change of image brightness. Particularly, the impact of histogram equalization, brightening and darkening of the image on the repeatability of the detectors is evaluated.
Databáze: OpenAIRE