We deomonstrate the potential for fruitful interaction between those studying artificial vision systems and those studying biological vision systems with the task of inferring global curves with corners and bifurcations from images. The talk outlines one slice through a large project on the computational neurobiology of vision. The Dilemma of Curve Detection from previous ones in that no attempt is made to match curves directly against the image, or even against measurements (i.e., "curve operators") evaluated over the image. Instead we stress the organizational point that a stable, reliable, but coarse description should be computed as an intermediate between the image (measurements) and the global curves. A particular intermediate representation—the discrete tangent field—is proposed.

The problem of obtaining reliable estimates of the optic flow field and its variation is discussed. It is argued that circuitry in the middle temporal (MT) visual area is arranged to provide mean field approximations of the optical flow field, that is, the maximal neighborhood over which the local field can be well-approximated as uniform, parallel translation. In addition, the way the mean field approximation varies with neighborhood size and position is informative about the variation of the flow field. It is shown how receptive fields can be synthesized to represent the first-order differential information about the flow field. The same ideas are applicable to the binocular disparity vector field, and lead one to predict the existence of extrastriate neurons that are specialized for the local shear and stretch of the disparity and motion vector fields.>

The problem of detecting curves in visual images arises in both computer vision and biological visual systems. Our approach integrates constraints from these two sources and suggests that there are two different stages to curve detection, the first resulting in a local description, and the second in a global one. Each stage involves a different style of computation: in the first stage, hypotheses are represented explicitly and coarsely in a fixed, preconfigured architecture; in the second stage, hypotheses are represented implicitly and more finely in a dynamically constructed architecture. We also show how these stages could be related to physiology, specifying the earlier parts in a relatively fine-grained fashion and the later ones more coarsely.

We propose a new paradigm for curve detection in which an autonomous and atomic description is computed between measurements on the image and global curves. The description takes the form of a discrete tangent field, i.e.. an estimated representation of quantized tangents and curvatures at each possible trace point. We then present a new algorithm for inferring global curves through this tangent field. by inferring a covering of the global curve. The elements of the covering are short splines, each of which moves according to a potential distribution computed from the tangent field. Both stages of the algorithm are parallel and both bear some analogy to biological mechanisms for curve detection