Priority-Based Path Growing for Linear Feature Detection

Linear feature detection is a very important step in image analysis, computer vision, and pattern recognition. It has a wide range of applications. In this paper, we present a new algorithm for linear feature detection using priority- based path growing from automatically selected seeds. The use of path growing in the neighbourhood of automatically selected seeds ensures that all local information along a linear feature is taken into account. This enables tracing of weakly contrasted linear features in an image. We illustrate our method with examples.