Research on image matching method based on improved Salp Swarm Algorithm optimization algorithm

Aiming at the problems of low matching rate and slow speed of traditional image matching methods, an image matching method (MSSA) based on the mutual learning mechanism based on the optimization algorithm of salp swarm optimization was proposed. The traditional salp swarm algorithm has the disadvant...

Full description

Saved in:

Bibliographic Details
Published in:	2023 IEEE 7th Information Technology and Mechatronics Engineering Conference (ITOEC) Vol. 7; pp. 2176 - 2185
Main Authors:	Zhang, Jinguang, Kang, Jianzhun, Shen, Xiaochun, Wang, Linggui, Zhang, Huanlong, Zhang, Haibei
Format:	Conference Proceeding
Language:	English
Published:	IEEE 15-09-2023
Subjects:	Feature extraction Image matching Intelligent optimization algorithm Learning systems Mechatronics Mutual learning mechanism Particle swarm optimization Salp swarm algorithm Sociology Statistics
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Aiming at the problems of low matching rate and slow speed of traditional image matching methods, an image matching method (MSSA) based on the mutual learning mechanism based on the optimization algorithm of salp swarm optimization was proposed. The traditional salp swarm algorithm has the disadvantages of low optimization accuracy and poor population diversity at the later stage of the iteration, by introducing a mutual learning mechanism, the problem of low population diversity of the salp swarm optimization at the later stage of the iteration is solved, and the convergence speed and accuracy of the algorithm are improved. the improved salp swarm algorithm is transformed into a target matching process. The histogram of oriented gradient is used to extract feature from image blocks to achieve accurate target matching. Finally, 10 classical test functions and CEC2014 test set were used to evaluate the effectiveness of the algorithm. The experimental results show that the improved salp swarm algorithm has a good application in image matching.
ISSN:	2693-289X
DOI:	10.1109/ITOEC57671.2023.10291882