Multi-Objective Boundary Tracking Method in Grayscale Image

DOI

10.2991/jiaet-18.2018.8How to use a DOI?

Keywords

grayscale image; multi-objective; gradient map; boundary tracking; seed point

Abstract

As for complex grayscale image, a kind of adaptive boundary tracking method for multi-objective is proposed in this paper. First of all, the grayscale image with noise is processed by Gaussian filter. Secondly, the image gradient after filtering is calculated. According to the geometric characteristics of ridge formed by edge points in gradient map, the new definition of seed points is put forward, which ensures the seed points in the seed point set must be ridge points, namely, edge points, and that there is at least one point in the edge points of the objectives belongs to the seed point set. Starting from the seed points, the boundary of all objectives can be tracked. The numerical experiments show that the method of this paper can adaptively track the multi-objective boundary in the complex grayscale image, and has a certain noise resistance and relatively strong robustness.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Shengyuan YANG
AU  - Shanshan XU
AU  - Xiaoyun ZENG
AU  - Yuanyuan PAN
PY  - 2018/03
DA  - 2018/03
TI  - Multi-Objective Boundary Tracking Method in Grayscale Image
BT  - Proceedings of the 2018 Joint International Advanced Engineering and Technology Research Conference (JIAET 2018)
PB  - Atlantis Press
SP  - 42
EP  - 49
SN  - 2352-5401
UR  - https://doi.org/10.2991/jiaet-18.2018.8
DO  - 10.2991/jiaet-18.2018.8
ID  - YANG2018/03
ER  -