Tutorial on Visual Information Retrieval @ ICDIM 2018
Information discovery based on the emerging technology to analyse digital images
Vrije Universiteit Brussel
In Reshaping libraries: emerging global technologies and trends. ICRL-2018. Papers of the First International Conference on Reshaping Libraries: Emerging Global Technologies and Trends organized jointly by DELNET-Developing Library Network, Ambedkar University Delhi in Association with the Society for Library Professionals (SLP) and Special Libraries Association (SLA, USA) Asian Chapter, February 1-3 at Jaipur, India. Chief Editor: H.K. Kaul, Editors P.K. Jain, Debal C. Kar, Sangeeta Kaul. Published by DELNET, New Delhi. ISBN 978-93-82735-13-7. 230 pp., pp. 1-14.
This offers a brief overview of the growing value of images in information discovery. Searching for images with a classical text query is a well-established, fast method to retrieve relevant images plus related textual information. ‘Search by image’ or ‘reverse image searching’ or ‘reverse image lookup’ on the WWW is a relatively new method, in which a search query consists not of text, but of an image file. The search results lead to related images and also to related documents on the WWW. This method of searching can be applied to cope with several types of information needs for which more classical search methods fail or perform less efficiently. This approach allows to discover duplicate images and even images that have elements in common with the image in the search query. Furthermore, the technology is improving towards discovery of images that are not only visually related, but also semantically related; this can yield information about the contents of the image used in the query. A search query can also include both text and an image; this can yield results with a higher precision than more simple queries. Recommendations for practitioners / users / librarians / information managers can be found at the end of the paper.
Google, information discovery, information retrieval, precision, reverse image searching, search by image, search services, search systems, semantic gap, TinEye