184 Visual Perception of Objects
this image before usually perceive it as a seemingly random
array of meaningless black blobs on a white background.
After they have discerned the Dalmatian with its head down,
sniffing along a street, however, the picture becomes dramat-
ically reorganized, with certain of the blobs going together
because they are part of the dog and others going together be-
cause they are part of the street or the tree. The interesting
fact relevant to past experience is that after you have seen the
Dalmatian in this picture, you will see it that way for the
rest of your life! Past experience can thus have a dramatic
effect on grouping and organization, especially if the organi-
zation of the image is highly ambiguous.
Region Segmentation
There is an important logical gap in the story of perceptual
organization that we have told thus far. No explanation
has been given of how the to-be-grouped “elements” (e.g.,
the dots and lines in Figure 7.2) arise in the first place.
Wertheimer (1923/1950) appears simply to have assumed the
existence of such elements, but notice that they are not di-
rectly given by the stimulus array. Rather, their formation
requires an explanation, including an analysis of the factors
that govern their existence as perceptual elements and how
such elements might be computed from an optical array of lu-
minance values. This initial organizational operation is often
calledregion segmentation:the process of partitioning an
image into an exhaustive set of mutually exclusive two-
dimensional areas.
Uniform Connectedness
Palmer and Rock (1994a, 1994b) suggested that region seg-
mentation is determined by an organizational principle that
they called uniform connectedness. They proposed that the
first step in constructing the part-whole hierarchy for an
image is to partition the image into a set of uniformly con-
nected (UC) regions, much like a stained glass window. A
region is uniformly connected if it constitutes a single, con-
nected subset of the image that is either uniform or slowly
varying in its visual properties, such as color, texture, motion,
and binocular disparity. Figure 7.1 (B) shows a plausible set
of UC regions for the leopard image, bounded by the solid
contours and labelled as regions 1 through 10.
Uniform connectedness is an important principle of per-
ceptual organization because of its informational value in
designating connected objects or object parts in the environ-
ment. As a general rule, if an area of the retinal image consti-
tutes a UC region, it almost certainly comes from the light
reflected from a single, connected, environmental object or
part. This is not true for successful camouflage, of course, but
such situations are comparatively rare. Uniform connected-
ness is therefore an excellent heuristic for finding image
regions that correspond to parts of connected objects in the
environment.
Figure 7.6 (B) shows how an image of a penguin (Fig-
ure 7.6; A) has been divided into a possible set of UC regions
by a global, explicitly region-based procedure devised by
Malik and his colleagues (Leung & Malik, 1998; Shi &
Malik, 1997). Their “normalized cuts” algorithm is a graph
theoretic procedure that works by finding the binary partition
of a given region—initially, the whole image—into two sets
of pixels that maximizes a particular measure of pairwise
pixel similarity within the same subregion, normalized rela-
tive to the total pairwise pixel similarity within the entire
region. Similarity of pixel pairs is defined in their algorithm
by the weighted integration of a number of Gestalt-likeA
Figure 7.6 A gray-scale image of a penguin (A), a regional segmentation of that image using Malik’s normal-
ized cuts algorithm (B), and the output of the Canny edge detection algorithm (C). Source: Parts A and B from
Shi and Malik, 1997; part C courtesy of Thomas Leung.