Two image-based search tools are available from Europeana: vieu (European Cultural Heritage Visual Search) and VIRaL (Visual Image Retrieval and Localization).
vieu is a visual image search engine focusing on cultural heritage content. Starting from a random set of images from the available collection, one can invoke a query and get a list of matching images ranked by visual similarity. In the results page, the visual similarity score is dispayed on top of each returned image, along with two basic options. The “details” option shows how the similarity between the image and the query was determined. The “original” option links directly to the source of the original image with all related information. Currently the source of all images is the Europeana portal, where each item is also linked to the content provider. Clicking on each returned image issues a new query.
VIRaL is a content-based image search engine. The query is an image, either uploaded, fetched from a given a URL, or chosen from the VIRaL database. Given this single image, it retrieves visually similar images from the database and estimates its location. VIRaL also suggests tags that may be attached to the query image, identifies known landmarks or points of interest, and provides links to relevant Wikipedia articles.
VIRaL also includes two additional functions: VIRaL Explore, which enables browsing of the entire VIRaL image collection on the world map, and VIRaL Routes, which constructs a route on a map showing icons of places visited (after images are processed and grouped with appropriate location information offline). An example of VIRaL Routes is depicted above.
Google Goggles is a mobile app that uses images to search the Internet. Not long ago Google introduced their reverse-image search to the web; the concept of Google Goggles is similar, but takes functionality even further. For example: not sure who designed that famous building you’re seeing as a tourist in Rome? Having trouble translating that Italian dinner menu? Want more information about a book, logo, bottle of wine, or painting? There’s now an app for that!
Additionally, in collaboration with Google, the Metropolitan Museum of Art has made 76,000 two-dimensional works of art from their collection accessible through Google Goggles. If you want to know more about a work of art exhibited in the museum, you can take a picture and search for it via Google Goggles to quickly see authoritative and contextual information from the Met. This information will also display if you see a work belonging to the Met in a book, on a banner, or elsewhere in the world. Check out this video from the Metropolitan Museum of Art for an illustrated introduction to the partnership.
The app is free and available on both iPhone (iOS 4.0) and Android (2.1+) platforms. If you’ve already downloaded iOS 5.0 for iPhone, the app won’t work, but we hope that a fix for this is under development!
Via Technology in the Arts.
Did you know? You can now drag image files from your computer into the Google Image search bar to perform an image-based search. Like Tineye, this ability to do a reverse search for images may help users connect images lacking data with information on the Internet. Google will also tell you the pixel dimensions of your image and link to alternate sizes, if available.
Last week CLAROS launched its first public web-based search interface, allowing users to discover digital resources from multiple collections of international art at once. Emphasis is placed on the art of Ancient Greece and Rome.
Based at the e-Research Centre in Oxford, CLAROS is an international research collaboration to enable simultaneous searching of major collections of digital material about archaeology and art in university research institutes and museums. It contains material from a wide range of data partners, including the Beazley Archive, various digital archives in the Ashmolean Museum, the Arachne archive, the Lexicon of Greek Personal Names, and the Lexicon Iconographicum Mythologiae Classicae, recording over 2 million objects, places, photographs, and people.
CLAROS provides keyword searching as well as browsing based on category, place, period, text and collection. It also performs reverse image searches of pottery and sculpture. This means users can upload an image or point to an image on the web and CLAROS will try to match it with those in the collections.
Via CLAROS: The World of Art on the Semantic Web
TinEye is a reverse image search engine. You can submit an image to TinEye to find out where it came from, how it is being used, if modified versions of the image exist, or to find higher resolution versions. TinEye is the first image search engine on the web to use image identification technology rather than keywords, metadata or watermarks.
TinEye is a helpful tool for identifying stray images as well. A stray slide without a label or a digital file without proper metadata may be uploaded and compared to similar images on the web. For answers to frequently asked questions about TinEye, or to view a short instructional video, click here.