Corpus-Based Thesaurus Construction for Image Retrieval in Specialist Domains

This paper explores the use of texts that are related to an image collection, also known as collateral texts, for building thesauri in specialist domains to aid in image retrieval. Corpus linguistic and information extraction methods are used for identifying key terms and conceptual relationships in specialist texts that may be used for query expansion purposes. The specialist domain context imposes certain constraints on the language used in the texts, which makes the texts computationally more tractable. The effectiveness of such an approach is demonstrated through a prototype system that has been developed for the storage and retrieval of images and texts, applied in the forensic science domain.

• Type: Conference
• Year: 2003
• Where: ECIR
• Authors: Khurshid Ahmad, Mariam Tariq, Bogdan Vrusias, Chris Handy
• Keywords: ECIR 2003, Information Technology, Specialist Domain, Specialist Texts, Texts