作者: Katerina Pastra , Horacio Saggion , Yorick Wilks
DOI: 10.1016/S0950-7051(03)00033-9
关键词: Data model 、 Visual Word 、 Latent semantic indexing 、 Information retrieval 、 Image retrieval 、 Application domain 、 Search engine indexing 、 Crime scene 、 Computer science 、 Information system
摘要: This paper presents work on text-based photograph indexing and retrieval for crime investigation, an application domain where efficient querying of large crime-scene databases is crucial importance. Automating this task will change current police practices considerably, by bringing 'intelligence' to support information systems. The prototype presented, goes beyond common approaches the automation image retrieval, applying a novel method that captures deep semantic relations expressed in captions accompany photographs. extraction these triples based advanced knowledge-based Natural Language Processing technologies resources.