Content-based image retrieval (CBIR); Image retrieval; Image retrieval system
Given a collection of images, a full-fledged image database provides means and technologies that support an efficient and rich modeling, storing, indexing, retrieval, and manipulation of images and its metadata. The modeling of images can range, depending on the used metadata format (e.g., MPEG-7), from simple technical annotations such as file size, creator, etc., to more sophisticated annotations such as low-level features (e.g., color) or even high-level features (e.g., objects, events, etc.). The storing component is responsible for mapping the used metadata format to an adequate database schema. Indexing facilities should support efficient retrieval and need to provide means (depending on the used metadata) for indexing text, multidimensional feature vectors, and high-level representations. The retrieval and query specification should support some or all of the following concepts:...
- 3.Shatford S. Analyzing the subject of a picture: a theoretical approach. Cat Classif Q. 1986;6(3):39–62.Google Scholar
- 5.Veltkamp RC, Tanase M. Content-based image retrieval systems: a survey, technical report. The Netherlands: Utrecht University; 2000.Google Scholar
- 7.Gupta A, Weymouth T, Jain R. Semantic queries with picture: the VIMSYS model. In: Proceedings of the 17th Conference on Very Large Databases; 1991. p. 69–79.Google Scholar
- 8.Besufekad SA. Modélisation et traitement de requêtes images complexes, PhD-thesis, L’Institut National des Sciences Appliquées de Lyon, 2003.Google Scholar
- 10.Christopher JC. Burges, dimension reduction: a guided tour. Mach Learn. 2010;2(4):275–365.Google Scholar