Image splicing detection method based on particle swarm optimization (PSO) algorithm

DOI

10.2991/icmemtc-16.2016.314How to use a DOI?

Keywords

splicing detection; support vector machine (SVM); particle swarm optimization (PSO)

Abstract

Splicing is copy-move operation on different image, and it is one of the most commonly used operations of image tampering. Aiming at the poor performance on detection, a kind of image splicing detection method based on particle swarm algorithm is proposed. First, we extracted two different image features: Markov and gray level co-occurrence matrix (GLCM) in the image database, which are used to verify the effectiveness of the particle swarm algorithm on different features. Then, we normalized the extracted image features to reduce the impact of identification results which comes from the singular value. Finally, the optimal SVM classification model was obtained by using the particle swarm optimization algorithm. Experiment on the two different features of the image database of Columbia University shows that the image splicing detection method based on particle swarm can improve the detection rate on different features, and achieve the best recognition rate of 93.20% on Markov features.

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  - Ling Gan
AU  - Xiao Liu
AU  - Kuanzhong Zou
PY  - 2016/04
DA  - 2016/04
TI  - Image splicing detection method based on particle swarm optimization (PSO) algorithm
BT  - Proceedings of the 2016 3rd International Conference on Materials Engineering, Manufacturing Technology and Control
PB  - Atlantis Press
SP  - 1651
EP  - 1656
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmemtc-16.2016.314
DO  - 10.2991/icmemtc-16.2016.314
ID  - Gan2016/04
ER  -