Application of BP Neural Network with Chebyshev Mapping in Image Compression
- Resource Type
- Conference
- Authors
- Yan, Shiqiang; Xiao, Zhong
- Source
- 2013 Third International Conference on Instrumentation, Measurement, Computer, Communication and Control Instrumentation, Measurement, Computer, Communication and Control (IMCCC), 2013 Third International Conference on. :398-402 Sep, 2013
- Subject
- Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Fields, Waves and Electromagnetics
Signal Processing and Analysis
Neurons
Biological neural networks
Image coding
Chebyshev approximation
Training
Heuristic algorithms
Chaotic communication
chaotic map
BP neural network
image compression
- Language
The traditional BP neural network has two disadvantages: long training time and easily getting into local minimum. To solve above problem, the neural network with chaotic neuron was proposed. In this paper, the Chebyshev chaotic mapping is used to construct the neural network. In order to evaluate its performance, the scheme of image compression by the neural network was given. The traditional BP and the Chebyshev chaotic neural networks are applied in the image compression. The result of simulation test shows that chaotic neural network is superior to BP network in the effect of image reconstruction.