Discriminating figure from ground: the role of edge detection and region growing.

Abstract

Three general classes of algorithms have been proposed for figure/ground segregation. One class attempts to delineate figures by searching for edges, whereas another class attempts to grow homogeneous regions; the third class consists of hybrid algorithms, which combine both procedures in various ways. The experiment reported here demonstrated that humans use a hybrid algorithm that makes use of both kinds of processes simultaneously and interactively. This conclusion follows from the patterns of response times observed when humans tried to recognize degraded polygons. By blurring the edges, the edge-detection process was selectively impaired, and by imposing noise over the figure and background, the regiongrowing process was selectively impaired. By varying the amounts of both sorts of degradation independently, the interaction between the two processes was observed.One of the fundamental purposes of vision is to allow us to recognize objects. Recognition occurs when sensory input accesses the appropriate memory representations, which allows one to know more about the stimulus than is apparent in the immediate input (e.g., its name). Before visual input can be compared to previously stored information, the regions of the image likely to correspond to a figure must be segregated from those comprising the background. The initial input from the eyes is in many ways like a bit-map image in a computer, with only local properties being represented by the activity of individual cells; only after the input is organized into larger groups, which are likely to correspond to objects and parts thereof, can it be encoded into memory and compared to stored representations of shape. Thus, understanding of the processes that segregate figure from ground is of fundamental importance for understanding the nature of perception.Researchers in computer vision have been faced with the problems of segregating figure from ground, and in this report we explore whether the human brain uses some of the algorithms they have developed. In computer vision, the input is a large intensity array, with a number representing the intensity of light at each point in the display. Two broad classes of algorithms have been devised to organize this welter of input into regions likely to correspond to objects. One class contains edge-based algorithms (1-3). These algorithms look first for sharp changes in intensity (i.e., maxima in first derivatives or zero crossings in the second derivative of the function relating intensity to position), which are assumed to correspond to edges. In the Marr-Hildreth theory (3), these changes are observed at multiple scales of resolution and, if present at each, are taken to indicate edges (and not texture or the like). The local points of sharp change are connected, resulting in a depiction of edges that are assembled into the outlines of objects. The other class contains the so-called region-based algorithms (4-7). These algorithms construct regions by growing and splitting areas that are maximally homogeneo...

Visual attention and perceptual grouping

“…In any case, it seems clear that texture segregation is an "edge-based" operation (Mumford, Kosslyn, Hillger, & Herrnstein, 1987). Perceptual grouping, on the other hand, can lend cohesion to a region (or several regions) within the field of view and clearly seems to be a "region-based" operation (Mumford et al, 1987). In addition to perceptual cohesion, however, grouping also creates an internal structure or organization in the affected region.…”

The proper placement of uniform connectedness

“…Consequently, the homogeneity of regions has been a relatively neglected variable; as such, it may deserve to be emphasized so that its influence can be evaluated. The study of how uniform connectedness combines with other organizational cues will certainly provide evidence critical for perceptual theory (see, e.g., Mumford, Kosslyn, Hillger, & Herrnstein, 1987). Of course, research alone can determine whether or not uniform connectedness occupies the privileged position assigned to it by Palmer and Rock.…”

Psychophysical evidence for fast region-based segmentation processes in motion and color.

“…Yet most human psychophysical studies of image segmentation have not focused on the distinction between edge-based and region-based segmentation, with some notable exceptions (13,14). Mumford et al (14) showed that in the luminance domain, the human visual system uses a hybrid algorithm that is sensitive both to the luminance variation within a region and to the sharpness of its edges.In the natural world, the human visual system must combine information from different attributes to find object boundaries and distinguish surfaces. We ask herein whether the segmentation processes based on different attributes are themselves different.…”