||AZILE: an intelligent verbal interface for the retrieval of pictorial architectural information
||The proliferation of on-line image databases and the utility of these images havetriggered the development of content-based techniques for indexing and retrieval.Most techniques are characterized by a verbal interpretation of visual patterns forquery formulation. The paper describes the integration of such verbal terms forarchitectural pictorial information in AZILE, a natural language interface thatoperates through a dialogue with the user. In this dialogue the user expressesqueries as normal everyday utterances. These are parsed and matched to athesaurus of architectural terms and concepts. The meaning and associations ofthese terms result into a preliminary fuzzy classification of available pictorialinformation. The purpose of AZILE is three-fold. Firstly, it serves as an incrementalrefinement of the query. Secondly, it facilitates direct retrieval of suitableinformation in a browsing fashion. Thirdly, it supports machine learning byautomatically indexing of the images with the terms identified in the user'sutterances.
|Year of publication:
Koutamanis A (2002).
AZILE: an intelligent verbal interface for the retrieval of pictorial architectural information. Agger K (ed.); Distributing knowledge in building; Arhus, June 12 - 14, Denmark (ISSN: 2706-6568),