拉盖尔-高斯模式噪声图像识别的神经网络

Optical Technologies for Telecommunications Pub Date : 2022-07-21 DOI:10.1117/12.2631735

Dmitry P. Bukin, E. Kozlova

{"title":"拉盖尔-高斯模式噪声图像识别的神经网络","authors":"Dmitry P. Bukin, E. Kozlova","doi":"10.1117/12.2631735","DOIUrl":null,"url":null,"abstract":"In this paper, the effect of different noises on Laguerre-Gaussian (LG) modes recognition by convolution neural network (CNN). A dataset of halftone images with LG modes and noises was prepared during the study. It is shown that not only intensity but also type of noise has high influence on classification process. However, presence of noisy images in the training sample allows to increase the recognition accuracy from 50% to 100% in most cases.","PeriodicalId":424251,"journal":{"name":"Optical Technologies for Telecommunications","volume":"22 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Neural network for recognition noisy images of Laguerre-Gaussian modes\",\"authors\":\"Dmitry P. Bukin, E. Kozlova\",\"doi\":\"10.1117/12.2631735\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, the effect of different noises on Laguerre-Gaussian (LG) modes recognition by convolution neural network (CNN). A dataset of halftone images with LG modes and noises was prepared during the study. It is shown that not only intensity but also type of noise has high influence on classification process. However, presence of noisy images in the training sample allows to increase the recognition accuracy from 50% to 100% in most cases.\",\"PeriodicalId\":424251,\"journal\":{\"name\":\"Optical Technologies for Telecommunications\",\"volume\":\"22 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-07-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Optical Technologies for Telecommunications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1117/12.2631735\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Optical Technologies for Telecommunications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1117/12.2631735","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 2

摘要

本文研究了不同噪声对卷积神经网络(CNN)识别拉盖尔-高斯(Laguerre-Gaussian, LG)模式的影响。在研究过程中，制备了具有LG模式和噪声的半色调图像数据集。结果表明，噪声强度和噪声类型对分类过程都有较大影响。然而，在大多数情况下，训练样本中存在噪声图像可以将识别准确率从50%提高到100%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Neural network for recognition noisy images of Laguerre-Gaussian modes

In this paper, the effect of different noises on Laguerre-Gaussian (LG) modes recognition by convolution neural network (CNN). A dataset of halftone images with LG modes and noises was prepared during the study. It is shown that not only intensity but also type of noise has high influence on classification process. However, presence of noisy images in the training sample allows to increase the recognition accuracy from 50% to 100% in most cases.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Optical Technologies for Telecommunications

自引率

0.00%

发文量