基于人工免疫的BP神经网络在图像压缩中的应用
pplication of BP neural network based of artificial immune to image compression
神经网络和人工免疫算法都是基于智能信息处理理论的进化算法，但是各自都存在一些缺陷。本文设计并实现了基于人工免疫的BP神经网络算法（AI-BP），它首先采用免疫算法进行全局搜索最优解，然后调用BP神经网络算法进行局部搜索，从而加快收敛速度。用基于实数编码的人工免疫算法优化神经网络的权值后，应用于图像压缩.实验证明，利用此AI-BP算法进行图像压缩比单独的BP神经网络进行图像压缩的收敛速度快、压缩比高、图像恢复质量效果好。
rtificial neural networks(ANN) and Artificial Immune(AI) are both theories for intelligent information processing，but there are limitations in these algorithms. Designing a BP neural networks based on Artificial Immune(AI-BP),It first utilizes the immune algorithm to have a global search ,and then uses BP algorithm to have a local search ,which will improve the speed of convergence. The experimental results show that the mixed algorithm can avoid premature saturation and have higher compression rate and better effect in image compression.
韩仁达、谢克明
计算技术、计算机技术
图像压缩人工免疫BP神经网络
image compressionrtificial Immune(AI)BP neural network
韩仁达,谢克明.基于人工免疫的BP神经网络在图像压缩中的应用[EB/OL].(2009-03-16)[2025-08-10].http://www.paper.edu.cn/releasepaper/content/200903-562.点此复制
评论