Tripod - Automating Caption Creation
The primary objective of Tripod is to revolutionise access to the enormous body of visual media. Applying an innovative multidisciplinary approach Tripod will utilise largely untapped but vast, accurate and regularly updated sources of semantic information to create ground breaking intuitive search services, enabling users to effortlessly and accurately gain access to the image they seek from this ever expanding resource.
Next generation photographs
Any image with either a reference to a location or explicit coordinates (collected through integrated camera GPS) can be exploited, thus enabling Tripod to both enhance the quality of legacy image captions and to automate captioning and indexing of next generation photographs collected with embedded spatial metadata.
Image: Tripod will build semantic descriptions of permanent man-made features.
Location as startingpoint
Taking as the starting point the location where a photo was taken (from GPS-coordinates or existing simple captions) Tripod will automatically build rich multi-faceted text and semantic descriptions of the landscape and permanent man-made features pictured in a photograph. On the other hand, Tripod will create image search facilities that serve broader user needs than current keyword or content-based approaches provide. See more in: www.ProjectTripod.org
