郭振军,,
朱昌洪
桂林航天工业学院 桂林 541004
基金项目:2019年度广西高校中青年教师科研基础能力提升项目(2019KY0802)，桂林航天工业学院电子信息重点学科及物联网与大数据应用研究中心项目(KJPT201805)
详细信息
作者简介:梁晓萍：女，1992年生，硕士，研究方向为计算机图像处理等
郭振军：男，1977年生，高级工程师，博士，研究方向为物联网及应用、无线传感网等相关技术
朱昌洪：男，1978年生，高级工程师，研究方向为物联网及应用、无线传感网等相关技术
通讯作者:郭振军 zjguo666@126.com
中图分类号:TP391计量
文章访问数:2467
HTML全文浏览量:2310
PDF下载量:57
被引次数:0
出版历程
收稿日期:2019-04-17
修回日期:2019-09-03
网络出版日期:2019-09-12
刊出日期:2019-12-01
BP Neural Network Fuzzy Image Restoration Basedon Brain Storming Optimization Algorithm
Xiaoping LIANG,Zhenjun GUO,,
Changhong ZHU
Guilin University of Aerospace Technology, Guilin 541004, China
Funds:2019 Guangxi University Young and Middle-aged Teachers’ Basic Scientific Research Ability Improvement Project (2019KY0802), The Project of Guilin University of Aerospace Technology Electronic Information Key Discipline and Internet Of Things and Big Data Application Research Center (KJPT201805)
摘要
摘要:该文提出一种基于头脑风暴智能优化算法的BP神经网络模糊图像复原方法(OBSO-BP)。该方法在聚类和变异两方面优化了头脑风暴智能算法，利用头脑风暴优化算法易于解决多峰高维函数问题的特点，自动搜寻BP神经网络更佳的初始权值和阈值，以减少BP网络对其初始权值和阈值的敏感性，避免网络陷入局部最优解，增加网络的收敛速度，减小网络误差，提高图像还原质量。该文采用20张不同的图像，对其模糊图像分别进行维纳滤波复原(Wiener)、基于头脑风暴算法的维纳滤波复原(Wiener-BSO)、BP神经网络复原以及基于头脑风暴算法的BP神经网络(BSO-BP)图像复原实验。实验结果表明，该方法能够取得更好的图像复原效果。
关键词:图像复原/
BP神经网络/
头脑风暴算法
Abstract:A kind of restoration method of BP neural network fuzzy image based on Optimized Brain Storming intelligent Optimized(OBSO-BP) algorithm is proposed in this paper. With the method of brain storming intelligent optimized algorithm which is optimized in both clustering and variation, issues of multi-peak high-dimensional function is easily solved. This method optimizes brain storming intelligence algorithm from two aspects of clustering and mutation. This method makes use of the characteristics of brain storming optimization algorithm, which is easy to solve multi-peak and high-dimensional function problems, to automatically search for better initial weights and thresholds of BP neural network, thus reducing the sensitivity of BP network to its initial weights and thresholds, avoiding the network falling into local optimal solution, increasing the convergence speed of the network and reducing the network error and improving the quality of image restoration. Twenty different images are adopted to the image restoration experiment of their fuzzy images with Wiener filtering restoration(Wiener), Wiener filtering restoration based on optimized Brain Storming intelligent Optimized algorithm(Wiener-BSO), BP neural network restoration and BP neural network restoration based on optimized Brain Storming intelligent Optimized algorithm(BSO-BP). Results show that a better effect of image restoration can be achieved with this method.
Key words:Image restoration/
BP neural network/
Brain storming algorithm
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=793ea7b7-46b3-4c38-8fc5-380f1adb60bf
