We describe an approach to detecting, locating and normalizing road signs. The approach will apply provided: (i) the signs have stereotypical boundary shapes (i.e. rectangular, or hexagonal-of course, we allow for these shapes to be distorted by projection to unknown viewpoint), (ii) the writing on the sign has one uniform color and the rest of the sign has a second uniform color (we allow for the color of the illuminant to be unknown). We show that the approach works even under significant illuminant color changes, viewpoint direction, shadowing, and occlusion. This work is part of a project intended to help people who are blind, or whose sight is impaired.

The authors describe a model of nonlinear image filtering for noise reduction and edge enhancement using anisotropic diffusion. The method is designed to enhance not only edges, but corners and T junctions as well. The method roughly corresponds to a nonlinear diffusion process with backward heat flow across the strong edges. Such a process is ill posed, making the results depend strongly on how the algorithm differs from the diffusion process. Two ways of modifying the equations using simulations on a variable grid are studied.>

A model is described for image segmentation that tries to capture the low-level depth reconstruction exhibited in early human vision, giving an important role to edge terminations. The problem is to find a decomposition of the domain D of an image that has a minimum of disrupted edges-junctions of edges, crack tips, corners, and cusps-by creating suitable continuations for the disrupted edges behind occluding regions. The result is a decomposition of D into overlapping regions R/sub 1/ union . . . union R/sub n/ ordered by occlusion, which is called the 2.1-D sketch. Expressed as a minimization problem, the model gives rise to a family of optimal contours, called nonlinear splines, that minimize length and the square of curvature. These are essential in the construction of the 2.1-D sketch of an image, as the continuations of disrupted edges. An algorithm is described that constructs the 2.1-D sketch of an image, and gives results for several example images. The algorithm yields the same interpretations of optical illusions as the human visual system.>