|
|
Search Options | Help | Site Map | Cultivate Web Site |
|
||
| Home | Current Issue | Index of Back Issues |
| Issue 1 Home | Editorial | Features | Regular Columns | News & Events | Misc. | ||
By Paul Allen, Roberto Vaccaro and Gert Presutti - July 2000
This article focuses on the description of the objectives of the ARTISTE project (for "An integrated Art Analysis and Navigation environment") that aims at building a tool for the intelligent retrieval and indexing of high resolution images.
European museums and galleries are rich in cultural treasures but public access has not reached its full potential. Digital multimedia can address these issues and expand the accessible collections. However, there is a lack of systems and techniques to support both professional and citizen access to these collections.
The ARTISTE project will address professional users in the fine arts as the primary end-user base. These users provide services for the ultimate end-user, the citizen.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
The possibility of an easy and effective management of large data repository is a strategic objective for many enterprises. This field of research is of particular interest to the market, as the availability of large repositories of electronic data is increasing and the industrial interest to solve the problem of automated content-based indexing and retrieval of images is high [1].
European museums and galleries are rich in cultural treasures but public access to masterpieces for education, leisure or work purposes has not reached its full potential. Automation of the indexing, retrieval and delivery of such assets over the web would help to address these issues and expand the accessibility of collections, broadening public awareness of the European cultural heritage, which lies behind them. To date, however, there has been a lack of systems and techniques to provide effective remote access to these collections [2],[3],[4].
New technology is now being developed that will transform that situation. A European consortium, partly funded by the EU under the fifth R&D framework, is working to produce a new management system for visual information.
Four major European galleries (The Uffizi in Florence, The National Gallery and the Victoria and Albert Museum in London and the Louvre related restoration centre, Centre de Recherche et de Restauration des Musées de France) are involved in the project. They will be joining forces with NCR, a leading player in database and Data Warehouse technology; Interactive Labs, the new media design and development facility of Italy's leading art publishing group, Giunti; IT Innovation, Web-based system developers; and the Department of Electronics and Computer Science at the University of Southampton. Together they will create web based applications and tools [5] for the automatic indexing and retrieval of high-resolution art images by pictorial content and information.
The 2.7 million Euro project called ARTISTE (An integrated Art Analysis and Navigation Environment) will take two and a half years to complete. It will give providers, publishers, distributors, rights protectors and end users of art images information, as well as the multi-media information market as a whole, a more efficient system for storing, classifying, linking, matching and retrieving art images. The system will be used in publishing, collection management, decision taking and life long training applications in the on-line information society of the new millennium.
The areas of innovation in this project are as follows:
The project represents a radical departure in terms of indexing works of art. Attempts have been made to index the objects and subjects in paintings using ordered systems, but these rely on expert knowledge of the content and in-depth experience of the classification system. The ARTISTE approach will use the power of object-related databases and content-retrieval to enable indexing to be made dynamically, by non-experts.
The high quality of images in the system, particularly in terms of colour, will allow comparisons to be made that in the past were based on information of too low a quality to support the assertions made. Comparisons made using the shadow data will allow comparison of brush strokes, etc.
Not much research has been carried out worldwide on new algorithms for style-matching in art. This is probably not a major aim in Artiste but could be a spin-off if the algorithms made for specific author search requirements happen to provide data which can be combined with other data to help classify styles.
In terms of colour matching all previous work has been non-colorimetric, i.e. varied RGB colour comparisons. The ARTISTE approach will use the unique collection of CIE colour values from the Vasari/Marc projects to carry out accurate colour comparisons. Preliminary work at UOS MMRG in this area shows that one can even begin to match reconstructed spectra with pure pigment spectra. The ability to put a colour value from say a colour meter reading of a pure known pigment in as a query to obtain a search across a collection would to ARTISTE. With similarly accurate collections such as those in the Uffizi gallery it is also possible to allow authors to find comparisons between collections, which were just not possible with non-calibrated images. NGL's fading data can also be used to provide clues about matching to colours before 100 years of light fading for example. This could help in cases such as textile/fabric sample matching.
Based on experience from working with art historians and art gallery professionals for 10 years UOS MMRG is aware of requirements in retrieval of art, rather than classification. In other words ARTISTE would aim to give searchers tools which hint at links due to say colour or brush-stroke texture rather than saying "this is the automatically classified data". Also by concentrating on specific examples such as fabric finding, pigment finding, specific shapes etc., we are producing new research results rather than trying to satisfy a huge array of users, which has been shown to be the weakest approach in content-based retrieval.
The ARTISTE project will build on and exploit the indexing scheme proposed by the AQUARELLE consortia. The ARTISTE project solution will have a core component that is compatible with existing standards such as Z39.50. The solution will make use of emerging technical standards XML, RDF and X-Link to extend existing library standards to a more dynamic and flexible metadata system. The ARTISTE project will actively track and make use of existing terminology resources such as the Getty "Art and Architecture Thesaurus" (AAT) and the "Union List of Artist Names" (ULAN).
ARTISTE will integrate art collections while allowing the owners of each collection to maintain ownership and control of their data. This will be achieved by virtually integrating the collections using the concept of distributed linking. The distributed linking will add links to content (both text and images) at presentation time. This will enable a user to add links to content that they do not own or have write access to.
Distributed links will ease the management of links by separating them from the content. This means that new links can be applied to an existing resource without modification to that resource (for example when a new image content analysis algorithm has been performed on the data set). In addition, different sets of links can be applied depending on the user viewing the resource.
The proposed architecture will allow multiple distributed databases to be integrated, removing the need for centralised repositories. However, as volumes are expected to exceed a terabyte, ARTISTE will use scalable object-relational database technology to manage these large data volumes.
Figure 1 shows the envisaged architecture for a fully implemented system.
Representations of the works of art are held in the object relational database as user defined modules (UDM). These UDMs define both the representations of the art and the functions that can be applied to these representations. These functions will include image processing and recognition techniques such as icon and painting technique detection. Hierarchical storage using disks and DVD technology will be used to store the images, as appropriate.
Metadata will also be stored in a database. This may be stored in the same object-relational database, or in a separate database, according to the incumbent systems at the user partners.
RDF provides for metadata definition through the use of schemas. Schemas define the relevant metadata terms (the namespace) and the associated semantics. Individual RDF queries and statements may use multiple schemas. The system will make use of existing schemas such as the Dublin Core schema and will provide wrappers for existing resources such as the Art and Architecture thesaurus in a RDF schema wrapper.
 |
| Figure 1: Artiste architecture |
The Distributed Query and Metadata Layer will provide a single interface to the art and its metadata. This layer will accept RDF queries and retrieve the relevant art document, either by formulating and executing a content-analysis SQL query in real-time, or by querying the metadata database using the common metadata schemas as necessary. The layer will map the RDF metadata namespace on to the metadata representation within the database. This mapping may be different for different galleries.
The Distributed Query and Metadata Layer will also provide facilities to enable queries to be directed towards multiple distributed databases. The end user will be able to seamlessly search the combined art collection. This layer will adhere to worldwide digital library standards such as Z39.50, augmenting and extending as necessary to allow the richness of metadata enabled by the RDF standard.
The presentation layer will provide the navigation facilities. Links will be added in real-time to the images, which is retrieved from the database, either through a local copy of the authored links database or through automatic generation from the metadata repository.
It will be possible to display the images in a standard Web browser. Use will be made of Java applets where necessary.
In conclusion the Artiste project will result into an interesting and innovative system for the art analysis, indexing storage and navigation. The actual state of the art of content-based retrieval systems will be positively influenced by the development of the Artiste project, which will pursue the following goals:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Paul Allen
IT Innovation Centre
2 Venture Road
Chilworth Science Park
Southampton
England
SO16 7NP
United Kingdom
<pja@it-innovation.soton.ac.uk>
<http://www.it-innovation.soton.ac.uk>
Phone: +44 (23) 8076 0834
Roberto Vaccaro
Giunti Interactive Labs
Giunti Interactive Labs S.r.l
via al Ponte Calvi, 3/15
16124 Genova
Italy
<r.vaccaro@giuntilabs.it>
<http://www.giuntilabs.com/>
Phone: +39 (010) 2465178
Gert Presutti
NCR SE-Copenhagen
Vibevej 20
2400 Copenhagen NV
Denmark
<Gert.Presutti@NCR.COM>
<http://www.NCR.dk/SE-Copenhagen/>
Phone: +45 (38) 15 75 47
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
For citation purposes:
Allen, P. Vaccaro, R, & Presutti, G. "Artiste: An integrated Art Analysis and Navigation Environment",
Cultivate Interactive, issue 1, 3 July 2000
URL: <http://www.cultivate-int.org/issue1/artiste/>
Translation:
If you wish to translate this page choose the preferred language using the
WorldLingo icon below.
Cultivate Interactive is not responsible for the outcome of this translation software. For further information see a previous article on Machine Translation.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Feedback:
If you wish to read or submit comments on this article we now provide
access to the Crit annotation service.
Before using this service you should read the guidelines.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
|
|
Use the Crit service