Image retrievaf based on semantic contents involves extraction, modelling and indexing of content information.While extraction of abstract contents is a hard problem, it is only part of the bigger picture.In this paper we use knowledge about the semantic contents of images to improve retrieval effectiveness.In particular we use Word Net, an electronic Iexicaf system for query and database expansion.Our content model facilitates novel uses of WordNet.We also propose a new normalization formula, an object significance scheme and evaluate their effectiveness with real user experiments.We describe the experiment setup and provide quantitative evaluation of each technique.

We make use of a refined E-R model to represent the contents of pictures. We propose remedies to handle mismatches which may arise due to differences in perception of picture contents. An iconic user interface for visual query construction is presented. A naive user can specify his/her intention without learning a query language. A function which computes the similarity between a picture and a user's description is provided. Pictures which are sufficiently close to the user description, as measured by the similarity function, are retrieved. We present the results of a user-friendliness experiment to evaluate the user interface as well as retrieval effectiveness. Encouraging retrieval results and valuable lessons are obtained.>