Title :
Using wavelet networks in image compression
Author :
Weiwei Xiao ; Haiyan Liu
Author_Institution :
Coll. of Sci., North China Univ. of Technol., Beijing, China
Abstract :
At present, the combination of wavelet analysis and neural network is an active research area. This paper presents a method of image compression based on wavelet neural network. Wavelet network is the tight combination of wavelet decomposition and neural network, where wavelet basis function works as the activation function. Wavelet network is used to compress images in this paper, and the comparison between wavelet network and traditional neural network is presented here. The result shows that wavelet network method succeeded in improving performances and efficiency in image compression.
Keywords :
data compression; feedforward neural nets; image coding; wavelet transforms; activation function; image compression; wavelet analysis; wavelet decomposition; wavelet neural network; Biological neural networks; Image coding; Neurons; Training; Wavelet analysis; Wavelet transforms;
Conference_Titel :
Natural Computation (ICNC), 2011 Seventh International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-9950-2
DOI :
10.1109/ICNC.2011.6022148