Extracting Curvilinear Structures: A Differential Geometric Approach

In this paper a method to extract curvilinear structures from digital images is presented. The approach is based on differential geometric properties of the image function. For each pixel, the second order Taylor polynomial is computed by convolving the image with the derivatives of a Gaussian smoothing kernel. Line points are required to have a vanishing gradient and a high curvature in the direction perpendicular to the line. The use of the Taylor polynomial and the Gaussian kernels leads to a single response of the filter to each line. Furthermore, the line position can be determined with sub-pixel accuracy. Finally, the algorithm scales to lines of arbitrary width. An analysis about the scale-space behaviour of two typical line types (parabolic and bar-shaped) is given. From this analysis, requirements and useful values for the parameters of the filter can be derived. Additionally, an algorithm to link the individual line points into lines and junctions that preserves the maximum number of line points is given. Examples on aerial images of different resolution illustrate the versatility of the presented approach.