Connectionists: texture segregation, grouping, attention, learning, painting

[Stephen Grossberg]

The following two articles are now available at 
http://www.cns.bu.edu/Profiles/Grossberg :

Grossberg, S.
The Art of Seeing and Painting.
Spatial Vision, in press, special issue on Art and Neuroscience

ABSTRACT
The human urge to represent the three-dimensional world using 
two-dimensional pictorial representations dates back at least to 
Paleolithic times. Artists from ancient to modern times have 
struggled to understand how a few contours or color patches on a flat 
surface can induce mental representations of a three-dimensional 
scene. This article summarizes some of the recent breakthroughs in 
scientifically understanding how the brain sees that shed light on 
these struggles. These breakthroughs illustrate how various artists 
have intuitively understand paradoxical properties about how the 
brain sees, and have used that understanding to create great art. 
These paradoxical properties arise from how the brain forms the units 
of conscious visual perception; namely, representations of 
three-dimensional boundaries and surfaces. Boundaries and surfaces 
are computed in parallel cortical processing streams that obey 
computationally complementary properties. These streams interact at 
multiple levels to overcome their complementary weaknesses and to 
transform their complementary properties into consistent percepts. 
The article describes how properties of complementary consistency 
have guided the creation of many great works of art.

Keywords: complementary computing, visual cortex, perceptual 
grouping, surface filling-in, figure-ground perception, amodal 
boundaries, perspective, T-junctions, opponent colors, neon color 
spreading, watercolor illusion, chiaoscuro, complementary 
consistency, Impressionism, Fauvism, Matisse, Monet, Hawthorne, 
Hensche, Leonardo da Vinci
******************************************

Bhatt, R., Carpenter, G., and Grossberg, S.
Texture segregation by visual cortex: Perceptual grouping, attention, 
and learning.
Vision Research, in press

ABSTRACT
A neural model called dARTEX is proposed of how laminar interactions 
in the visual cortex may learn and recognize object texture and form 
boundaries. The model unifies five interacting processes: 
region-based texture classification, contour-based boundary grouping, 
surface filling-in, spatial attention, and object attention. The 
model shows how form boundaries can determine regions in which 
surface filling-in occurs; how surface filling-in interacts with 
spatial attention to generate a form-fitting distribution of spatial 
attention, or attentional shroud; how the strongest shroud can 
inhibit weaker shrouds; and how the winning shroud regulates learning 
of texture categories, and thus the allocation of object attention. 
The model can discriminate abutted textures with blurred boundaries 
and is sensitive to texture boundary attributes like discontinuities 
in orientation and texture flow curvature as well as to relative 
orientations of texture elements. The model quantitatively fits the 
Ben-Shahar & Zucker (2004) human psychophysical data on 
orientation-based textures. Surface-based attentional shrouds improve 
texture learning and classification: Brodatz texture classification 
rate varies from 95.1% to 98.6% with correct attention, and from 
74.1% to 75.5% without attention. Object boundary output of the model 
in response to photographic images is compared to computer vision 
algorithms and human segmentations.

Keywords: Texture segregation, object recognition, image 
segmentation, perceptual grouping, spatial attention, object 
attention, attentional shroud, visual cortex, Adaptive Resonance 
Theory