Learning imprecise semantic concepts from image databases

In this paper we introduce a model to represent high-level semantic concepts that can be perceived in images. The concepts are learned and represented by means of a set of association rules that relate the presence of perceptual features to the fulfillment of a concept for a set of images. Since bot...

Descripción completa

Detalles Bibliográficos
Autores: Sánchez Fernández, Daniel, Chamorro Martínez, Jesús
Tipo de recurso: artículo
Fecha de publicación:2002
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2099/3618
Acceso en línea:https://hdl.handle.net/2099/3618
Access Level:acceso abierto
Palabra clave:Fuzzy association rule
Perceptual feature
Image semantics
Intel·ligència artificial
Classificació AMS::68 Computer science::68T Artificial intelligence
Descripción
Sumario:In this paper we introduce a model to represent high-level semantic concepts that can be perceived in images. The concepts are learned and represented by means of a set of association rules that relate the presence of perceptual features to the fulfillment of a concept for a set of images. Since both the set of images where a perceptual feature appears and the set of images fulfilling a given concept are fuzzy, particularly because of user's subjectivity, we use in fact fuzzy association rules for the learning model. The concepts so acquired are useful in several applications, in particular they provide a new way to formulate imprecise queries in image databases. An additional feature of our methodology is that it can capture user's subjectivity.