Construction of image retrieval systems focused on user knowledge interaction

  • Authors:
  • Tomoko Kajiyama;Shin'ichi Satoh

  • Affiliations:
  • Aoyama Gakuin University, Kanagawa, Japan;National Institute of Informatics, Tokyo, Japan

  • Venue:
  • Proceedings of the international conference on Multimedia
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Our objective was to apply different kinds of database with our proposed graphical search interface, and to verify the effectiveness focused on user knowledge structure in searching because it allowed users to easily modify received information to suitable knowledge. This interface was for multi-faceted metadata named Concentric Ring View. The design concept of this interface is "result-oriented", which means users continue to search by evaluating the retrieved results. We constructed four image retrieval systems with images designed for web pages, flower, insect, and country. We selected databases from two aspects; the gap between images and information features, and the necessity of general knowledge to understand values of information features. To make users more able to understand the relationship between retrieved results and attributes values, we added independent functions depending on the features of database, e.g., preparing images focused on search keys, mapping to meaningful area like a world map. We confirmed that this interface bridged the gaps by materializing user knowledge from abstract images, and that users learned with our system and modified users' knowledge structure without general knowledge. This interface can be used not only as a retrieval system but also as an educational system.