Funded by the Independent News and Media, Imprezzeo says that the search engine is more advanced than other similar technologies in the market, as it combines content-based image retrieval (CBIR) and facial recognition technologies. The technology has been built on Java and C++ by the University of Queensland and the University of Wollongong in Australia.
Users can select a sample image from the initial set of images and refine their search, irrespective of the size of the pictures. They can also upload images from their own collection to search for similar ones. Users can use pictures such as landmarks, objects, graphics, people or personalities to find what they want.
Dermot Corrigan, CEO of Imprezzeo, said: “This will fundamentally change the way users and consumers expect to search for images, whether that’s in a photo stock library, the desktop or the web. We know that currently many image searches are abandoned at the first set of results, because the returned results are not what the user is looking for. This technology changes that.”
Initially, Imprezzeo targets the enterprise users, particularly media -- stock photo libraries, news agencies, and publishers. It plans to expand to web image search, web photo-hosting, sharing and finishing, and retail in future.
In May this year, Idee, a developer of image identification and visual search software, has launched the beta of a similar image-based search engine, TinEye, where users can upload a picture and see where it appears on the web. Vodafone Germany has also introduced its image-based mobile search engine in 2008. Mobile users can click an image from their phone and MMS it to a service to get more information about the picture.