{"title":"基于人工神经网络的光学涡旋亚像素定位","authors":"A. Popiołek-Masajada, E. Fraczek, Emilia Burnecka","doi":"10.24425/mms.2021.137131","DOIUrl":null,"url":null,"abstract":"Optical vortices are getting attention in modern optical metrology. Because of their unique features, they can be used as precise position markers. In this paper, we show that an artificial neural network can be used to improve vortex localization. A deep neural network with several hidden layers was trained to find subpixel vortex positions on the spiral phase maps. Several thousand training samples, differing by spiral density, its orientation, and vortex position, were generated numerically for teaching purposes. As a result, Best Validation Performance of the order of 10−5 pixel has been reached. To verify the usefulness of the proposed method, a related experiment in the setup of an optical vortex scanning microscope has been reported. It is shown that the vortex can be localized with subpixel accuracy also on experimental phase maps.","PeriodicalId":18394,"journal":{"name":"Metrology and Measurement Systems","volume":" ","pages":""},"PeriodicalIF":1.1000,"publicationDate":"2023-07-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Subpixel localization of optical vortices using artificial neural networks\",\"authors\":\"A. Popiołek-Masajada, E. Fraczek, Emilia Burnecka\",\"doi\":\"10.24425/mms.2021.137131\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Optical vortices are getting attention in modern optical metrology. Because of their unique features, they can be used as precise position markers. In this paper, we show that an artificial neural network can be used to improve vortex localization. A deep neural network with several hidden layers was trained to find subpixel vortex positions on the spiral phase maps. Several thousand training samples, differing by spiral density, its orientation, and vortex position, were generated numerically for teaching purposes. As a result, Best Validation Performance of the order of 10−5 pixel has been reached. To verify the usefulness of the proposed method, a related experiment in the setup of an optical vortex scanning microscope has been reported. It is shown that the vortex can be localized with subpixel accuracy also on experimental phase maps.\",\"PeriodicalId\":18394,\"journal\":{\"name\":\"Metrology and Measurement Systems\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2023-07-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Metrology and Measurement Systems\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.24425/mms.2021.137131\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"INSTRUMENTS & INSTRUMENTATION\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Metrology and Measurement Systems","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.24425/mms.2021.137131","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"INSTRUMENTS & INSTRUMENTATION","Score":null,"Total":0}
Subpixel localization of optical vortices using artificial neural networks
Optical vortices are getting attention in modern optical metrology. Because of their unique features, they can be used as precise position markers. In this paper, we show that an artificial neural network can be used to improve vortex localization. A deep neural network with several hidden layers was trained to find subpixel vortex positions on the spiral phase maps. Several thousand training samples, differing by spiral density, its orientation, and vortex position, were generated numerically for teaching purposes. As a result, Best Validation Performance of the order of 10−5 pixel has been reached. To verify the usefulness of the proposed method, a related experiment in the setup of an optical vortex scanning microscope has been reported. It is shown that the vortex can be localized with subpixel accuracy also on experimental phase maps.
期刊介绍:
Contributions are invited on all aspects of the research, development and applications of the measurement science and technology.
The list of topics covered includes: theory and general principles of measurement; measurement of physical, chemical and biological quantities; medical measurements; sensors and transducers; measurement data acquisition; measurement signal transmission; processing and data analysis; measurement systems and embedded systems; design, manufacture and evaluation of instruments.
The average publication cycle is 6 months.