WIREDGOV

A massive global computer grid, designed to analyse the unprecedented amounts of data generated by the Large Hadron Collider LHC, the world’s biggest scientific experiment, is being utilised by two high tech start-up companies from Cambridge, who are working together to build the next generation of internet search engine.

These two Cambridgeshire companies, Imense Ltd and iLexIR Ltd have created a joint venture, Camtology, to use their individual expertise and products together to search both text and images online. Imense Ltd is building the next generation of image search, developing innovative solutions that make retrieval of images even easier and more powerful than any existing search for images on the Internet. iLexIR Ltd is focussing on natural language processing, aimed at identifying relevant information, as opposed to just looking at individual words in a document.

Both Imense and iLexIR are using GridPP to test and enhance their software. Funded by the Science and Technology Facilities Council (STFC), GridPP was built to be able to handle and analyse the UK’s share of the petabytes (one petabyte is one quadrillion bytes) of data that will be generated by the LHC annually, requiring huge data storage and processing capabilities.

Dr Liz Towns Andrews, Director of Knowledge Exchange at STFC said: "This is an excellent example of what happens when the possible wider applications of new research and technologies are considered. In this case, the Grid, that addresses the computing challenges faced by physicists analysing the vast amounts of science data generated by the Large Hadron Collider, is also solving the problems faced by Imense and iLexIR. STFC’s Knowledge Exchange Service was able to connect both companies to the GridPP team and provide modest funding to start them off. As a result both companies face a bright future benefiting the UK economy in the process."

With the aim of becoming the ‘Google’ of image searching, Imense has developed a search engine that will make sense of the huge numbers of pictures on the World Wide Web. Although images and video make up over 70% of digital data available on the internet, traditional software cannot index this information directly, relying totally on text descriptions entered by hand. Imense’s software can literally look at a photo and recognise the colours, shapes, objects and scenes. Imense’s key innovation is a new form of image retrieval that analyses images in terms of their content, without the need for human generated captions. It also uses an extremely powerful query language - the user just needs to type in a few keywords and the software is able to interpret the request and match it to relevant images on the basis of their visual content. The use of the Grid and its vast processing power has enabled Imense to test and demonstrate its software on sufficiently large numbers of photos, millions upon millions of images, which otherwise would have been impossible.

Dr David Sinclair, Co-founder of Imense said: "Although we had built a prototype of our image analysis software, we knew that we simply were not able to test our technology on enough images. We knew we could sample thousands of images, but to demonstrate a commercially viable product we needed millions of images, and just could not afford to do this. Access to the Grid with the help of STFC’s funding has provided us with access to the computing power and expertise required to demonstrate our technology which, in turn, impressed investors and led to funding for our company."

Imense’s partner in Camtology, iLexIR Ltd, is focussing on natural language processing. Current search engines present pages of results in order of expected relevance to a query, based on key words typed in by the user, resulting in vast numbers of irrelevant pages being returned and some important results not being presented. The use of natural language can help with both interpreting the query and also, crucially, with interpreting the pages with the potential answers. iLexIR is using the Grid to process huge amounts of text in documents, aiming at finding relevant information as opposed to just looking at individual words.

Recently, both Imense and iLexIR have separately received ‘PIPSS¹’ funding from STFC. PIPSS awards form part of STFC’s knowledge transfer scheme that supports the development of effective, long term collaborations between universities, UK industry and research oganisations, with the aim to ensure the maximum benefit to UK industry, through transfer of technologies and skills.

Imense’s initial proof of concept was developed following an STFC miniPIPSS² award, enabling the small company to obtain further venture capital funding. This funding allowed Imense to team up with a group of particle physicists at the University of Cambridge’s eScience Centre, who helped Imense to develop its software to run on the Grid and to demonstrate its capabilities. This demonstration resulted in further PIPSS funding which Imense is now using to show that the Grid can be used on a commercial scale for their application and means scaling up to process millions of images and reaching the levels of reliability required in real business. iLexIR has also very recently received an STFC miniPIPSS award which is enabling it to use the Grid to process huge amounts of text in documents, aiming at finding relevant information as opposed to just looking at individual words.

The joint venture, Camtology, has been set up by Imense and iLexIR to look at using both products together to search text and images, and has started work on bringing together their expertise into a demonstrator model. This could eventually provide a UK-based search engine which is capable of competing with the best current providers on the world stage, capturing a large share of the huge market for search services.

Notes to Editors

Images available

Images are available on request. Please contact Wendy Taylor.

Contacts:

Wendy Taylor MCIPR

Press Officer

Science and Technology Facilities Council Daresbury Laboratory Daresbury Science & Innovation Campus Daresbury Warrington Cheshire

WA4 4AD

Email: w.j.taylor@dl.ac.uk

Tel Number: 01925 603232

About PIPSS

¹PIPSS is a knowledge transfer scheme that supports the development of effective, long term collaborations between UK Universities, CERN, ESO (European Southern Observatory), ESA (European Space Agency), UK industry and research sector organisations, with the aim to ensure the maximum benefit to UK industry, through transfer of technologies and skills developed from the Council's research programme to broader market areas. PIPSS encourages a two-way transfer of skills and knowledge between the Council's supported scientists and researchers in UK industry and research organisations representing other sectors. The overall objective of PIPSS is to facilitate the transfer of technology developed in pursuit of the Council's science programme. In other words, to transfer Science and Technology Facilities Council developed technologies to other academic disciplines and/or industrial applications. ²The Mini-PIPSS provides the facility to make an application for a small project, up to £110k over a period not exceeding 12 months, at any time and receive a decision within a short period of time.

About GridPP

GridPP is a collaboration of twenty UK universities and research institutes, building and operating a computing Grid for particle physics. It is funded by STFC, with additional associated funding from HEFCE, SHEFC and the European Union.

Science and Technology Facilities Council The Science and Technology Facilities Council ensures the UK retains its leading place on the world stage by delivering world-class science; accessing and hosting international facilities; developing innovative technologies; and increasing the socio-economic impact of its research through effective knowledge exchange partnerships.

The Council has a broad science portfolio including Astronomy, Particle Physics, Particle Astrophysics, Nuclear Physics, Space Science, Synchrotron Radiation, Neutron Sources and High Power Lasers. In addition the Council manages and operates three internationally renowned laboratories:

• The Rutherford Appleton Laboratory, Oxfordshire

• The Daresbury Laboratory, Cheshire

• The UK Astronomy Technology Centre, Edinburgh

The Council gives researchers access to world-class facilities and funds the UK membership of international bodies such as the European Laboratory for Particle Physics (CERN), the Institute Laue Langevin (ILL), European Synchrotron Radiation Facility (ESRF), the European organisation for Astronomical Research in the Southern Hemisphere (ESO) and the European Space Agency (ESA). It also contributes money for the UK telescopes overseas on La Palma, Hawaii, Australia and in Chile, and the MERLIN/VLBI National Facility, which includes the Lovell Telescope at Jodrell Bank Observatory.

The Council distributes public money from the Government to support scientific research. Between 2008 and 2009 we will invest approximately £787 million.

The Council is a partner in the UK space programme, coordinated by the British National Space Centre.