European researchers have developed software that will help users organise, search and navigate digital images collections. The IMAGINATION (‘Image-based navigation in multimedia archives’) project, funded under the Information Society Technologies (IST) Thematic area of the EU’s Sixth Framework Programme (FP6), sought to bring digital cultural and scientific resources closer to their users, effectively making it easier for them to obtain important information about images and image parts. Financing for IMAGINATION totalled more than EUR 2.10 million.
The project partners anticipate that their software, ImageNotion, will hit the market in 2010. The software is user-friendly, they say, because the technology links the content of photos to concepts. The end result is that computers can understand the images in a way similar to humans.
The ImageNotion software succeeds in combining semantic annotation with various technologies. For instance, it can recognise objects, detect faces and carry out text data mining.
‘When you mention ontologies to most people, they just switch off,’ said Gabor Nagypal, technical and scientific coordinator of IMAGINATION. ‘A photographer, an image agency employee or a Web user doesn’t want and shouldn’t have to learn how the technology works; they just want to be able to use it. Because of that, our goal has been to make the technology transparent and intuitive to use.’
By combining technologies, the IMAGINATION consortium offers users the opportunity to save a great deal of time on tagging photos, for instance. According to Mr Nagypal, the face detection system can identify the presence of people in photos with an 80% success rate.
Face recognition is more challenging as it can generate consistent results after 5 to 10 images of a person have been tagged.
‘In a real-world environment, the accuracy will differ depending on a variety of factors, although for a professional image agency or photographer dealing with thousands of photos, any reduction in the amount of manual annotation needed makes a huge difference in terms of time and cost savings,’ said Mr Nagypal, who is a developer at the German software company disy Informationssysteme GmbH.
Another key component of the software is what the consortium calls ‘imagenotions’, the creation of ontology elements. According to the team, imagenotions can be customised and updated by end users whenever they want.
‘If they realise that a notion does not exist for a particular person or object, they can easily add it to the system,’ the project coordinator said. ‘For example, the system would automatically identify the first photo it comes across of Angela Merkel as a person and a woman,’ he explained. ‘The user could then define her profession as German chancellor and state that the photo was taken at a certain EU meeting. Those terms could then, with a few clicks, be used to pull up a list of other photos from the meeting and connect to information about other people who were present.’
ImageNotion is being tested by various users including the Italian State Library of Modern and Contemporary History and the French photo agency Photo12. The partners noted that a Web-based beta version is also available for testing on the ImageNotion Ltd website (http://www.imagenotion.com), a spin-off that was established for the software’s initial commercialisation.
‘We are currently refining the software, but we hope to be ready to start selling it as a stand-alone or Web-based product next year,’ Mr Nagypal said. ‘First, we will target professional users, primarily photo agencies, archives and libraries who need a quicker and easier way to annotate and find images, then we will look to provide it as a software service for individual photographers and, finally, as an embedded application, which could be used on other websites such as Facebook or Flickr.’