A Persistence-Based Approach to Automatic Detection of Line Segments in Images

Kurlin, Vitaliy ORCID: 0000-0001-5328-5351 and Muszynski, Grzegorz
(2019) A Persistence-Based Approach to Automatic Detection of Line Segments in Images. In: Computational Topology in Image Context.

[img] Text
CTIC2019PLSD_modified.PDF - Author Accepted Manuscript

Download (8MB)


Edge detection algorithms usually produce a discrete set of edgels (edge pixels) in a given image on a fixed pixel grid. We consider the harder problem of detecting continuous straight line segments at subpixel resolution. The state-of-the art Line Segment Detection Algorithm (LSDA) outputs unordered line segments whose total number cannot be easily controlled. Another motivation to improve the LSDA is to avoid intersections and small angles between line segments, hence difficulties in higher level tasks such as segmentation or contour extraction. The new Persistent Line Segment Detector (PLSD) outputs only non-intersecting line segments and ranks them by a strength, hence the user can choose a number of segments. The main novelty is an automatic selection of strongest segments along any straight line by using the persistence from Topological Data Analysis. The experiments on the Berkeley Segmentation Database of 500 real-life images show that the new algorithm outperforms the LSDA on the important measure of Boundary Recall.

Item Type: Conference or Workshop Item (Unspecified)
Uncontrolled Keywords: Topological persistence, Edge detection, Skeletonization
Depositing User: Symplectic Admin
Date Deposited: 24 Jan 2019 14:59
Last Modified: 19 Jan 2023 01:08
DOI: 10.1007/978-3-030-10828-1_11
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3030467