An unbiased detector of curvilinear structures

TLDR

Extraction of curvilinear structures is a key low‑level operation in computer vision, yet most existing operators rely on simple line models that ignore surrounding context. This paper proposes an algorithm that explicitly models both lines and their surroundings. By analyzing the scale‑space behavior of a model line profile, the method removes bias caused by asymmetrical lines. The resulting detector returns precise subpixel line positions and widths, correcting the misplacement that occurs with prior methods.

Abstract

The extraction of curvilinear structures is an important low-level operation in computer vision that has many applications. Most existing operators use a simple model for the line that is to be extracted, i.e., they do not take into account the surroundings of a line. This leads to the undesired consequence that the line will be extracted in the wrong position whenever a line with different lateral contrast is extracted. In contrast, the algorithm proposed in this paper uses an explicit model for lines and their surroundings. By analyzing the scale-space behavior of a model line profile, it is shown how the bias that is induced by asymmetrical lines can be removed. Furthermore, the algorithm not only returns the precise subpixel line position, but also the width of the line for each line point, also with subpixel accuracy.