Image retrieval with textual label similarity features

• Autores: Alicia Sagae, Scott E. Fahlman
• Localización: Intelligent systems in accounting, finance & management, ISSN-e 1099-1174, Vol. 22, Nº. 1, 2015, págs. 101-113
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • This article presents a knowledge-based solution for retrieving English descriptions of images. We analyse the errors made by a baseline system that relies on term frequency, and we find that the task requires deeper semantic representation. Our solution is to perform incremental, task-driven development of an ontology. Ontological features are then applied in a machine-learning algorithm for ranking candidate image descriptions. This work demonstrates the advantage of combining knowledge-based and statistical approaches for text retrieval, and it establishes the important result that an empirically tuned task-specific ontology performs better than a domain-general resource like WordNet, even on previously unseen examples.