一种基于BP神经网络的图像压缩方法
首发时间:2007-11-20
摘要:探讨了神经网络用于图像压缩和解压缩技术,实现了一种基于改进BP神经网络压缩方法:按图像各部分像素特征将图像分为平滑块、中间块和边缘块,不同的分类块采用不同的隐含层数,从而在保证重建图像丰富细节的同时,提高图像的压缩比。同时,对3层BP神经网络进行优化,提高了网络的收敛速率,实验结果证明本算法在取得较大的压缩比的同时能保证图像的恢复质量。
For information in English, please click here
An image compression coding algorithm based on BP neural network
Abstract:Neural network used in image compression and decompression is discussed in this article Then an image compression method based on improved BP network is developed.In this article we classify an image into three sections according to its pixel character. The BP algorithm is also bettered to improve the convergence velocity of BP neural network and the simulation results indicate that the compression rate and the decompression quantity are largely improved.
Keywords: image compression;Neural network BP algorithm
论文图表:
引用
No.1645459300119555****
同行评议
勘误表
一种基于BP神经网络的图像压缩方法
评论
全部评论0/1000