Image compression using multilayer neural networks based on Fast Bacterial Swarming Algorithm
- Resource Type
- Conference
- Authors
- Ying Chu; Hua Mi; Zhen Ji; Zi-Bo Shao
- Source
- 2008 International Conference on Machine Learning and Cybernetics Machine Learning and Cybernetics, 2008 International Conference on. 5:2890-2893 Jul, 2008
- Subject
- Computing and Processing
Robotics and Control Systems
Image coding
Artificial neural networks
Microorganisms
Optimization
Training
Nonhomogeneous media
Image reconstruction
Image compression
Multilayer neural network
Fast bacterial swarming algorithm
- Language
- ISSN
- 2160-133X
2160-1348
A novel multilayer neural network based on Fast Bacterial Swarming Algorithm (FBSA) for image compression is presented in this paper. The proposed novel neural network combines the traditional structure of two-layer symmetric Artificial Neural Network (ANN) and the newly presented FBSA, which demonstrates quick and good performance for high-dimensional function optimization problems. Comparison of the qualities of the reconstructed images had shown the effective improvement using the proposed algorithm than using the conventional BP network.