电子测量与仪器学报

许学彬,陈博桓,赵楠楠,沈洋,倪军.基于 GA-BP 的改进高斯均值区域去噪技术[J].电子测量与仪器学报,2022,36(2):107-113

基于 GA-BP 的改进高斯均值区域去噪技术

Improved gaussian mean region denoising technology based on GA-BP

DOI：

英文关键词:neural network images processing fiber optic connector optical engineering

基金项目:国家级大学生创新创业训练计划（202010356009）、浙江省公益技术研究计划（LGN20F050001）、国家重点研发计划（2020YFF0217803）项目资助

作者	单位
许学彬	1. 中国计量大学光学与电子科技学院
陈博桓	1. 中国计量大学光学与电子科技学院
赵楠楠	2. 中国计量大学质量与安全工程学院
沈洋	1. 中国计量大学光学与电子科技学院
倪军	1. 中国计量大学光学与电子科技学院

Author	Institution
Xu Xuebin	1. College of Optical and Electronic Technology, China Jiliang University
Chen Bohuan	1. College of Optical and Electronic Technology, China Jiliang University
Zhao Nannan	2. College of Quality and Safety Engineering, China Jiliang University
Shen Yang	1. College of Optical and Electronic Technology, China Jiliang University
Ni Jun	1. College of Optical and Electronic Technology, China Jiliang University

摘要点击次数: 847

全文下载次数: 559

中文摘要:

光纤连接器因其在光传输系统中的重要作用而备受关注,但是其表面附着的杂质会使复原的表面形貌出现噪点。而且现有的检测方法无法准确定位噪点,需要对其进行多次整体降噪处理,以此得到的图像细节保留能力较差。为此提出了一种基于遗传算法优化 BP 神经网络(GA-BP)的改进高斯均值区域去噪技术。首先,对干涉数据进行降维处理;其次,将降维后的数据作为神经网络的训练数据,利用神经网络对噪点进行定位;最后,采用改进的高斯均值滤波对三维图像的噪点位置进行滤波处理。结果表明,通过神经网络判别法得到的噪声像素点为 2. 45%,相比于阈值判别法具有较高的精度。并且通过改进的高斯均值滤波方法得到的方法噪声差值为 474. 7,峰值信噪比(PSNR)值为 32. 56。相比于均值和中值滤波方法,图像细节保持能力较高,复原图像噪点凸起明显减少。因此,它更适用于基于白光干涉原理的自动化检测。

英文摘要:

Optical fiber connectors have attracted much attention due to the essential role in optical transmission systems, but the impurities attached on the fiber surface will generate noise on the recovered morphology. Moreover, the existing detection methods cannot accurately locate the noise. It needs to be processed for multiple overall noise reduction, and the image detail retention ability obtained by this method is inadequate. To this end, we proposed an improved Gaussian mean region denoising technology based on GA-BP neural network. Firstly, the interference data is processed by dimensionality reduction. Secondly, select the dimensionality reduction data as the training data, and use the neural network to locate the noise. Finally, the improved Gaussian mean filter is used to filter the noise position of the three-dimensional image. Furthermore, the results show that the noise pixel obtained by the neural network discrimination method is 2. 45%, which is higher than the threshold discrimination method. And the noise difference obtained by the improved Gaussian mean filtering method is 474. 7, and the PSNR value is 32. 56. Compared with the mean and median filtering methods, the image detail retention ability is higher, and the restored image noise bulge is significantly reduced. Therefore, it is more suitable for automatic detection based on the principle of white light interference.

查看全文查看/发表评论下载PDF阅读器