Directional structures detection based on morphological line-segment and orientation functions

Abstract

In the present paper a morphological approach for segmenting directional structures is proposed. This approach is based on the concept of the line-segment and orientation functions. The line-segment function is computed from the supremum of directional erosions. This function contains the sizes of the longest lines that can be included in the structure. To determine the directions of the line segments, the orientation function which contains the angles of the line segments it is built when the line-segment function is computed. Next, by combining both functions, a weighted partition is built using the watershed transformation. Finally, the elements of the partition are merged according to some directional and size criteria for computing the desired segmentation of the image using a RAG structure. © 2008 Springer-Verlag Berlin Heidelberg.