Open AccessApplication of particle swarm optimization BP neural network algorithm in image compression
Author(s) -
Haijun Wang,
Jin Tao
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1550/2/022025
Subject(s) - particle swarm optimization , artificial neural network , algorithm , maxima and minima , multi swarm optimization , convergence (economics) , computer science , image compression , metaheuristic , image (mathematics) , mathematical optimization , mathematics , artificial intelligence , image processing , economics , economic growth , mathematical analysis
In order to overcome the problems of weak global search ability, slow convergence speed and easy to fall into local minima in the process of image compression of BP neural network model, an image compression model based on particle swarm optimization algorithm and improved BP algorithm is proposed. In this model, a group of optimal approximate solutions of weights and thresholds of BP network are obtained through global search of particle swarm optimization according to objective function, and then the approximate solution is taken as the initial value of BP model, and the improved BP algorithm is used to conduct quadratic optimization training on these weights and thresholds to obtain the final image compression model. The experimental results show that with the same error accuracy, the quality of model compressed image reconstruction based on particle swarm BP neural network algorithm is significantly higher than that of BP and improved BP algorithm models.