首页 | 本学科首页   官方微博 | 高级检索  
     检索      

改进误差反向传播(BP)神经网络在图像压缩中的应用
引用本文:李季.改进误差反向传播(BP)神经网络在图像压缩中的应用[J].应用光学,2013,34(6):974-979.
作者姓名:李季
作者单位:长春职业技术学院,吉林 长春 130033
摘    要: 针对空间遥感图像数据量剧增的问题,提出一种改进的BP神经网络图像压缩方法。该算法利用Levenberg-Marquart算法提高神经网络的收敛速度,利用α算法提高神经网络的泛化能力。比较分析了新算法和标准BP算法对同一幅图像进行压缩的结果和性能误差函数。实验结果表明,实验结果表明,标准BP算法在图像压缩比为1/2时,均方误差(MSE)为343.3750;改进后的BP算法在图像压缩比为1/16时,MSE为69.5796,图像压缩比为1/8时,MSE为20.9561,图像压缩比为1/4时,MSE为5.5123。并且利用改进后的算法压缩图像的峰值信噪比均在30 dB~40 dB之间。改进算法已用于实际工程中,满足实际需求。

关 键 词:BP神经网络  图像压缩  空间遥感图像  Levenberg-Marquart算法  &alpha  算法

Image compression used improved error back-propagation neural network
LI Ji.Image compression used improved error back-propagation neural network[J].Journal of Applied Optics,2013,34(6):974-979.
Authors:LI Ji
Institution:Changchun Vocational Institute of Technology, Changchun 130033, China
Abstract:To overcome the dramatically increasing data amount of space remote sensing image, an improved back-propagation(BP) neural network was put forward to compress it. The algorithm used the Levenberg-Marquart algorithm to improve the convergence speed of neural network and used α algorithm to improve the generalization ability of neural network. We compared and analyzed the compression result and error performance function of the improved algorithm and the standard BP algorithm to the same image. The experimental results show that, when the image compression ratio is 1/2, the mean square error (MSE) of standard BP algorithm is 343.3750; for improved BP algorithm, the MSE is 69.5796 when the image compression ratio is 1/16, the MSE is 20.9561 when the image compression ratio is 1/8, and the MSE is 5.5123 when the ratio is 1/4. Moreover, the peak signal-to-noise ratio (PSNR) of the improved algorithm is always in the range from 30 dB to 40 dB. The improved algorithm has been applied in practical engineering, which meets the need of practical work.
Keywords:BP neural network  image compression  space remote sensing image  Levenberg-Marquart algorithm  &alpha  algorithm
点击此处可从《应用光学》浏览原始摘要信息
点击此处可从《应用光学》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号