Perceptual Organization 185grouping factors, such as proximity, color similarity, texture
similarity, and motion similarity. They also include a group-
ing factor based on evidence for the presence of a local edge
between the given pair of pixels, which reduces the likeli-
hood that they are part of the same subregion. When this
normalized cuts algorithm is applied repeatedly to a given
image, dividing and subdividing it into smaller and smaller
regions, perceptually plausible partitions emerge rapidly
(Figure 7.6; B). Notice that Malik’s region-based approach
produces closed regions by definition.
Another possible approach to region segmentation is to
begin by detecting luminance edges. Whenever such edges
form a closed contour, they define two regions: the fully
bounded interior and the partly bounded exterior. An image
can therefore be segmented into a set of connected regions by
using an edge-detection algorithm to locate closed contours.
This idea forms a theoretical bridge between the well-known
physiological and computational work on edge detection
(e.g., Canny, 1986; Hubel & Wiesel, 1962; Marr & Hildreth,
1980) and work on perceptual organization, suggesting that
edge detection may be viewed as the first step in region seg-
mentation. An important problem with this approach is that
most edge-detection algorithms produce few closed contours,
thus requiring further processing to link them into closed con-
tours. The difficulty is illustrated in Figure 7.6 (C) for the out-
put of Canny’s (1986) well known edge-detection algorithm.
Texture Segmentation
A special case of region segmentation that has received con-
siderable attention is texture segmentation (e.g., Beck, 1966,
1972, 1982; Julesz, 1981). In Figure 7.1(A), for example, the
leopard is not very different in overall luminance from the
branch, but the two can easily be distinguished visually by
their different textures.
The factors that govern region segmentation by texture
elements are not necessarily the same as those that deter-
mine explicit judgments of shape similarity, even for the very
same texture elements when they are perceived as individual
figures. For instance, the dominant texture segmentation evi-
dent in Figure 7.7 (A)—that is to say, that separating the up-
rightTs and Ls from the tilted Ts—is the opposite of simple
shape similarity judgments (Figure 7.7; B) in which a single
uprightTwas judged more similar to a tilted Tthan it was
to an upright L(Beck, 1966). From the results of many such
experiments, texture segmentation is believed to result from
detecting differences in feature density (i.e., the number of
features per unit of area) for certain simple attributes, such as
line orientation, overall brightness, color, size, and move-
ment (Beck, 1972). Julesz (1981) later proposed a similar
theory in which textures were segregated by detecting
changes in the density of certain simple, local textural fea-
tures that he called textons(Julesz, 1981), which included
elongated blobs defined by their color, length, width, orienta-
tion, binocular disparity, and flicker rate, plus line termina-
tors and line crossings or intersections.
Julesz also claimed that normal, effortless texture segmen-
tation based on differences in texton densities was a preatten-
tiveprocess: one that occurs automatically and in parallel
over the whole visual field prior to the operation of focussed
attention. He further suggested that there were detectors early
in the visual system that are sensitive to textons such that
texture segmentation takes place through the differential
activation of the texton detectors. Julesz’s textons are similar
to the critical features ascribed to simple cells in cortical
area V1 (Hubel & Wiesel, 1962), and to some of the primitive
elements in Marr’s primal sketch (Marr, 1982; Marr &
Nishihara, 1978). Computational theories have since been
proposed that perform texture segmentation by detecting tex-
tural edges from the outputs of quasi-neural elements whose
receptive fields are like those found in simple cells of area V1
of the visual cortex (e.g., Malik & Perona, 1990).Figure-Ground OrganizationIf the goal of perceptual organization is to construct a scene-
based hierarchy consisting of parts, objects, and groups,
region segmentation can be no more than a very early step,
because uniform connected regions in images seldom corre-
spond directly to the projection of whole environmental
objects. As is evident from Figures 7.1 (A, B, and C), some
UC regions need to be grouped into higher-level units (e.g.,
the various patches of sky) and others need to be parsed intoA. Texture SegregationB. Shape Similarity
Figure 7.7 Texture segmentation of Ts, tilted Ts, and Ls (A) versus shape
similarity of the same letters (B). Source:From Palmer, 1999.