DocumentCode :
691038
Title :
Application of BP Neural Network with Chebyshev Mapping in Image Compression
Author :
Shiqiang Yan ; Zhong Xiao
Author_Institution :
Network Center, Univ. of Shijiazhuang Tiedao, Shijiazhuang, China
fYear :
2013
fDate :
21-23 Sept. 2013
Firstpage :
398
Lastpage :
402
Abstract :
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.
Keywords :
backpropagation; data compression; image coding; image reconstruction; neural nets; BP neural network; Chebyshev chaotic mapping; Chebyshev chaotic neural networks; chaotic neuron; image compression; image reconstruction; local minimum; long training time; Biological neural networks; Chaotic communication; Chebyshev approximation; Heuristic algorithms; Image coding; Neurons; Training; BP neural network; chaotic map; image compression;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Instrumentation, Measurement, Computer, Communication and Control (IMCCC), 2013 Third International Conference on
Conference_Location :
Shenyang
Type :
conf
DOI :
10.1109/IMCCC.2013.91
Filename :
6840480
Link To Document :
بازگشت