An adaptive neural network model for distinguishing line- and edge detection from texture segregation

Abstract

The authors consider an important paradigm in vision: distinguishing object contours or edges (and lines) from object surface textures. To accomplish this, an artificial neural network model, called the EDANN model, is used for both texture segregation and line and edge detection starting from a common bank of spatial filters. The model provides different representations of a retinal image in such a way that different actions and decisions about the presence of objects in the visual scene can be undertaken in a further stage. Three possible cases of distinguishing luminance-defined lines and edges from noise textures are considered.<>