The perceptual organization of image patterns is considered from 2 standpoi
nts. First, a theoretical framework is presented from which computational m
odels of perceptual organization can be constructed and tested. Second, a s
pecific computational model for perceptual organization of line images is d
escribed. In this model, input images are first processed by a dense array
of neurons that have properties consistent with recent analyses of single-n
euron responses in primary visual cortex. Then, complex image structure is
discovered by interleaved pattern-matching and grouping processes constrain
ed by a generalized uniqueness principle. A series of 3-pattern grouping ex
periments was performed to test a restricted version of the model and to es
timate critical parameters. Using the estimated parameters, an extended ver
sion of the model was tested by generating predictions for a series of "tex
tbook" perceptual organization demonstrations.