Personalized content based image retrieval

The significant increase in memory technology which provided a substantial boost to the capacity made available to the users as well as the emergence of digital and media technology created important challenges to information processing community as the search for efficient and effective digital image within the range of databases becomes a difficult task. This paper investigates the issue of image retrieval system in the light of LIRE open source system and put forward new formalism for combining text and image attributes. Typically, the image attributes consist of MPEG-7 visual descriptors scalar color, color layour, edge histogram and correlogram while the text attribute conveys the various annotations made by the user to describe the content of the image. Lucene text retrieval was used as a basis to integrate the text component. A similarity measure which reinforces the overlapping outcome among various attributes is put forward. Feasibility and evaluation of the proposal are investigated.