The Inner Structure of Database for the CBIR System

Jaworska, Tatiana

doi:10.1109/cimca.2008.197

Cited by 2 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to construct the required ontology, at first, we have analysed the existing CBIR database, to establish, which architectural elements have been recognized in the system [11]. Here, let us note that, in general, this step may not be as obvious as it seems.…”

Section: Ontology Constructionmentioning

confidence: 99%

“…The structure of the original database (see, [11]) has not been changed. We have only extended it by adding new tables or, at least, columns to the already existing tables.…”

Section: Databasementioning

confidence: 99%

“…The CBIR system that we have access to (and are in the process of extending), is being developed at the Systems Research Institute, Polish Academy of Sciences (SRI PAS)(for complete description of all aspects of already developed system, see [9,10,11,12]). At the time of writing of this contribution, the system uses four original modules, implemented in Matlab, for image segmentation and classification.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Combining semantic technologies with a content-based image retrieval system – Preliminary considerations

Chmiel

Ganzha

Jaworska

et al. 2017

AIP Conference Proceedings

View full text Add to dashboard Cite

Abstract. Nowadays, as a part of systematic growth of volume, and variety, of information that can be found on the Internet, we observe also dramatic increase in sizes of available image collections. There are many ways to help users browsing / selecting images of interest. One of popular approaches are Content-Based Image Retrieval (CBIR) systems, which allow users to search for images that match their interests, expressed in the form of images (query by example). However, we believe that image search and retrieval could take advantage of semantic technologies. We have decided to test this hypothesis. Specifically, on the basis of knowledge captured in the CBIR, we have developed a domain ontology of residential real estate (detached houses, in particular). This allows us to semantically represent each image (and its constitutive architectural elements) represented within the CBIR. The proposed ontology was extended to capture not only the elements resulting from image segmentation, but also "spatial relations" between them. As a result, a new approach to querying the image database (semantic querying) has materialized, thus extending capabilities of the developed system.

show abstract

Section: Ontology Constructionmentioning

confidence: 99%

“…The structure of the original database (see, [11]) has not been changed. We have only extended it by adding new tables or, at least, columns to the already existing tables.…”

Section: Databasementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation