WαSH-ing visual repositories: Searching Europeana using local features

Museums, libraries, national archives and art galleries deal with visual objects that must be made accessible to a wide variety of experts or non-experts like researchers, art lovers or interested people. The ability to identify objects sharing some aspect of visual similarity can be useful when trying to trace historical influences or when looking for further examples of paintings, sculptures or other cultural objects appealing to their taste. In this direction, we use our recent detector [1] for an image retrieval task on a subset of Europeana´s¹ content. The detector produces distinctive features by grouping sampled image edges according to proper shape stability measures. We evaluate the detector by integrating it into the Visual Search Engine for Europeana (Vieu)² tool.