In this paper we propose a model based on a conceptual space automatically induced from data. The model is inspired to a well-founded robotics cognitive architecture which is organized in three computational areas: sub-conceptual, linguistic and conceptual. Images are objects in the sub-conceptual area, that become "knoxels" into the conceptual area. The application of the framework grants the automatic emerging of image semantics into the linguistic area. The core of the model is a conceptual space induced automatically from a set of annotated images that exploits and mixes different information concerning the set of images. Multiple low level features are extracted to represent images and a set of single visual terms and spatially displaced couples of visual terms is computed. When a new image is mapped as a knoxel in the conceptual space, the most probable conceptual linguistic label automatically arise from the space. The technique has been tested on 2000 images of the Corel data set and results are reported.
A conceptual probabilistic model for the induction of image semantics
Vella F
2010
Abstract
In this paper we propose a model based on a conceptual space automatically induced from data. The model is inspired to a well-founded robotics cognitive architecture which is organized in three computational areas: sub-conceptual, linguistic and conceptual. Images are objects in the sub-conceptual area, that become "knoxels" into the conceptual area. The application of the framework grants the automatic emerging of image semantics into the linguistic area. The core of the model is a conceptual space induced automatically from a set of annotated images that exploits and mixes different information concerning the set of images. Multiple low level features are extracted to represent images and a set of single visual terms and spatially displaced couples of visual terms is computed. When a new image is mapped as a knoxel in the conceptual space, the most probable conceptual linguistic label automatically arise from the space. The technique has been tested on 2000 images of the Corel data set and results are reported.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.