2P1-E14 Cognitive Vision Inspired Feature Understanding in Intelligent Space

Abstract

This paper presents a visual cortex inspired cognitive modcl for feature understanding, integrated into a DIND, which is the basic unit of the Intelligent Space. The model is strongly based on the receptive field characteristics of cortical neurons of the visual cortex. As a step forward compared to the previous vcrsion of the model, a new dimension has been added, which replaccs the binary signals and operations by operations en real values. Thc resulting system yields a better approximation of the biological system,as well as provides stronger and more distinct contour lines and vertices. The contour detection and vertex extraction is performed by a vast network of simple units organized in a special structure, the Visual Feature Array (VFA). The goal of the model is to extract abstract information from an image, which in turn is used as input for other models understanding even more abstrttct visual objects, and thus allowing the Intelligent Space to acquire more abstract knowledge about its internal state.