Ordinal structure in the visual perception and cognition of smoothly curved surfaces

James T. Todd, Francene D. Reichel
1989 Psychological review  
In theoretical analyses of visual form perception, it is often assumed that the 3-dimensional structures of smoothly curved surfaces are perceptually represented as point-by-point mappings of metric depth and/or orientation relative to the observer. This article describes an alternative theory in which it is argued that our visual knowledge of smoothly curved surfaces can also be denned in terms of local, nonmetric order relations. A fundamental prediction of this analysis is that relative
more » ... judgments between any two surface regions should be dramatically influenced by the monotonicity of depth change (or lack of it) along the intervening portions of the surface through which they are separated. This prediction is confirmed in a series of experiments using surfaces depicted with either shading or texture. Additional experiments are reported, moreover, that demonstrate that smooth occlusion contours are a primary source of information about the ordinal structure of a surface and that the depth extrema in between contours can be optically specified by differences in luminance at the points of occlusion. For many higher organisms, including humans, a primary source of knowledge about objects and events in the surrounding environment is provided by vision. Because of the ecological importance of this knowledge, the processes of visual perception and cognition have been attracting a growing amount of attention in recent years from researchers in a variety of fields. There are two basic issues on which this research has primarily been focused: (a) identification of the relevant parameters of representation for visually based knowledge, and (b) determination of the specific sources of optical information from which it is obtained. Consider, for example, a recent theory of object recognition by Biederman (1987) that addresses both of these issues. According to Biederman, most objects in the environment can be adequately represented to achieve recognition using a limited set of volumetric primitives, called geons, which are connected to one another in simple combinations, in much the same way that words can be composed from a relatively small alphabet of phonemes. The optical information from which these geons are perceptually specified is assumed to be based on easily measureable properties of image contours, such as the presence or absence of curvature, parallelism, or symmetry, and the cotermination of contours at vertices. Biederman (1987) has pointed out that his analysis is re-
doi:10.1037//0033-295x.96.4.643 fatcat:duobfq6tofcpncbeqxwi3bl3ha