Junction detection for linear structures based on Hessian, correlation and shape information

Junctions have been demonstrated to be important features in many visual tasks such as image registration, matching, and segmentation, as they can provide reliable local information. This paper presents a method for detecting junctions in 2D images with linear structures as well as providing the number of branches and branch orientations. The candidate junction points are selected through a new measurement which combines Hessian information and correlation matrix. Then the locations of the junction centers are refined and the branches of the junctions are found using the intensity information of a stick-shaped window at a number of orientations and the correlation value between the intensity of a local region and a Gaussian-shaped multi-scale stick template. The multi-scale template is used here to detect the structures with various widths. We present the results of our algorithm on images of different types and compare our algorithm with three other methods. The results have shown that the proposed approach can detect junctions more accurately.

► In this study, we propose a new method for detecting junction points, branch numbers, and branch orientations.
► Propose a new measurement based on Hessian matrix and correlation matrix to select candidate junction points.
► Refine the locations of the junctions as well as detect the branch orientations.
► The approach is applied on several types of images.