A Feature Extraction Algorithm of Damaged Military Area Based on Fuzzy Connectedness

DOI

10.2991/ame-16.2016.223How to use a DOI?

Keywords

Fuzzy Connectedness, Region Growing, Feature Extraction.

Abstract

A region growing algorithm based on fuzzy connectedness is proposed in this thesis to solve the military targets' damage problems that the traditional region growing algorithm couldn't handle properly. In this algorithm, the fuzzy connectedness is regarded as the measurement of level of similarity between the growing point and the seed point, which helps to keep the fuzziness among pixels, and it grows according to the fuzzy connectedness in the order — from strong to weak to make the growing results insensitive to the selection of seed points. Besides this, the algorithm combines the gray level fluctuation and USAN area and regards it as the growth rule, which helps to adjust the gray level changes in target regions and the better edge positioning effect is achieved. The experimental results show the efficiency of the algorithm.

Copyright

© 2016, 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  - Ya-Hong Zhu
AU  - Rui Wang
AU  - Ji-Ping Cao
AU  - Cong-Wei Wu
PY  - 2016/06
DA  - 2016/06
TI  - A Feature Extraction Algorithm of Damaged Military Area Based on Fuzzy Connectedness
BT  - Proceedings of the 2nd Annual International Conference on Advanced Material Engineering (AME 2016)
PB  - Atlantis Press
SP  - 1368
EP  - 1372
SN  - 2352-5401
UR  - https://doi.org/10.2991/ame-16.2016.223
DO  - 10.2991/ame-16.2016.223
ID  - Zhu2016/06
ER  -