摘要
研究了一个3层BP网络的图像压缩方案,分别采用了不同的传输函数、不同的隐含层神经元数目和同一幅图像不同大小的分块方式,分析和总结BP网络压缩性能与各种网络参数之间的关系.结果表明:BP网络传输函数、隐含层神经元数目以及对原图像分块大小的不同,都会直接影响收敛时间和压缩性能.
The image compression scheme of a 3-layer BP network was studied in this paper.The relationship between BP network compression performance and network parameters was analysed and summarized using different transmission functions,different numbers of the hidden layer neurons and different dividing ways of the same image. The results showed that the convergence time and compression properties was affected by BP network transmission function,the number of the hidden layer neurons and different dividing ways of the original image directly.
出处
《河南科技学院学报(自然科学版)》
2014年第2期49-54,共6页
Journal of Henan Institute of Science and Technology(Natural Science Edition)
关键词
BP神经网络
BP算法
图像压缩
BP neural network
Back-propagation algorithm
image compressi