{"title":"计算机生成全息图在不同显示系统之间转换的深度神经网络及其训练策略","authors":"Juhyun Lee, Byoun-gkil Lee","doi":"10.1364/dh.2022.w2a.11","DOIUrl":null,"url":null,"abstract":"We propose a deep learning method to convert the given hologram for a display system to a new one for another system. The proposed method can be applied to adapt holograms to any component changes of different systems. In this paper, we set different wavelength of the light source for the original and target display system. Convolutional neural network is designed, and artificial hologram dataset is used for training. Numerically reconstructed images of the converted holograms are shown.","PeriodicalId":227456,"journal":{"name":"Digital Holography and 3-D Imaging 2022","volume":"158 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Deep neural network and its training strategy for converting computer-generated hologram between different display systems\",\"authors\":\"Juhyun Lee, Byoun-gkil Lee\",\"doi\":\"10.1364/dh.2022.w2a.11\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We propose a deep learning method to convert the given hologram for a display system to a new one for another system. The proposed method can be applied to adapt holograms to any component changes of different systems. In this paper, we set different wavelength of the light source for the original and target display system. Convolutional neural network is designed, and artificial hologram dataset is used for training. Numerically reconstructed images of the converted holograms are shown.\",\"PeriodicalId\":227456,\"journal\":{\"name\":\"Digital Holography and 3-D Imaging 2022\",\"volume\":\"158 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1900-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Digital Holography and 3-D Imaging 2022\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1364/dh.2022.w2a.11\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Digital Holography and 3-D Imaging 2022","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1364/dh.2022.w2a.11","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Deep neural network and its training strategy for converting computer-generated hologram between different display systems
We propose a deep learning method to convert the given hologram for a display system to a new one for another system. The proposed method can be applied to adapt holograms to any component changes of different systems. In this paper, we set different wavelength of the light source for the original and target display system. Convolutional neural network is designed, and artificial hologram dataset is used for training. Numerically reconstructed images of the converted holograms are shown.