CORDIS provides links to public deliverables and publications of HORIZON projects.
Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .
Exploitable results
The increasing volumes of images have created the need for more effective and efficient image indexing and searching, not only of the metadata associated with an image (e.g. captions, annotations) but also retrieval based directly on the content of the image.
COBWEB is a pioneer system that will provide a solution to the problem of automatically storing and retrieving images from large image databases dispersed over the Internet. For this purpose, the project focused on the development of effective algorithms for the automatic indexing of the visual features of imagery (e.g. colour, texture) that can be used as a means for retrieving similar images without the burden of manual indexing, although the ultimate objective is semantic based access to images.
A second important issue about COBWEB is the creation of a simple, useful and effective user interface. The interface will hide the system's internal complexity (e.g. feature extraction and indexing algorithms, search procedures) from the end-user and will help the user perform queries and retrieve images in the most "natural" way. Therefore, the user interface will provide retrieval tools, designed to match the human way of thinking.
Having in mind that the client's location may be remote, referring to the database's location, the above goals should be achieved in the most effective way, as far as time and costs are concerned. Thus, the architecture of the system in terms of communication between the various components is another quite important subject.
The main objectives of COBWEB are:
-To reduce the time and costs to store a new image in an existing image database. This will be achieved by dramatically reducing the need for textual annotation of image.
-To reduce the time and costs to retrieve an image from an existing image database. This will be achieved by dramatically increasing the precision of the retrieval process.
Searching for OpenAIRE data...
There was an error trying to search data from OpenAIRE
No results available