An image restoration algorithm based on improved RBF neural network

摘要：

　　In order to improve large amount of computing and slowly convergence speed,an improved radial basis function (RBF) neural network is raised in this paper.According to feature that the more recent data should be the more important in time-series data,it converts width value from original constant value to step function and accelerates the iterative convergence by using nearest neighbor clustering algorithm only at center,training weight by using gradient descent algorithm to correct network parameters and deleting input neurons adaptively.Network size is streamlined through network optimization training.Simulation shows that the restored image is good in visual and quantitative with faster image restoration processing.The algorithm based on improved RBF neural network has significantly improved the image restoration compared to other methods,but also well keeps image detail.

关键词： image restoration neural network image degradation

作者: Xuezhang Zhao Zhiyuan Liu Yunjiang Xi

作者单位: Foshan Polytechnic College Foshan, Guangdong province, China South China University of Technology Guangzhuo, Guangdong province, China

会议类型: 国际会议

会议名称: the 2012 International Conference on Frontiers of Advanced Materials and Engineering Technology (2012年先进材料与工程技术国际会议(FAMET 2012))

会议地点: 厦门

会议语种:英文

页码: 1671-1676

在线出版日期: 2012-01-04（万方平台首次上网日期，不代表论文的发表时间）