Full metadata record
DC FieldValueLanguage
dc.contributor.authorYang, Chia-Chien_US
dc.contributor.authorSu, Jian-Jiaen_US
dc.contributor.authorLi, Jie-Enen_US
dc.contributor.authorZhu, Zhi-Yuen_US
dc.contributor.authorTseng, Jin-Shingen_US
dc.contributor.authorCheng, Chu-Mingen_US
dc.contributor.authorTien, Chung-Haoen_US
dc.date.accessioned2020-05-05T00:02:00Z-
dc.date.available2020-05-05T00:02:00Z-
dc.date.issued2019-01-01en_US
dc.identifier.isbn978-1-5106-3112-0en_US
dc.identifier.issn0277-786Xen_US
dc.identifier.urihttp://dx.doi.org/10.1117/12.2542652en_US
dc.identifier.urihttp://hdl.handle.net/11536/154070-
dc.description.abstractEccentric infrared photorefraction is an attractive vision screening method which is widely used for uncooperative subjects, such as infants and toddlers. Unlike conventional slope-based photorefraction, a deep neural network is used to predict refractive error in this study. Total 1216 ocular image were collected by a homemade photorefraction device, whose corresponding refractive error was measured by a commercial autorefractor device, to create a series of dataset for our deep neural network. The mean squared error of the preliminary result is +/- 0.9 diopter, which indicates its feasibility and can be improved with bigger database.en_US
dc.language.isoen_USen_US
dc.subjectrefractive erroren_US
dc.subjectphotorefractionen_US
dc.subjectdeep learningen_US
dc.subjectdigital imaging processingen_US
dc.subjectoptical systemen_US
dc.titleAccessing Refractive Errors via Eccentric Infrared Photorefraction Based on Deep Learningen_US
dc.typeProceedings Paperen_US
dc.identifier.doi10.1117/12.2542652en_US
dc.identifier.journalSPIE FUTURE SENSING TECHNOLOGIESen_US
dc.citation.volume11197en_US
dc.citation.spage0en_US
dc.citation.epage0en_US
dc.contributor.department光電工程學系zh_TW
dc.contributor.departmentDepartment of Photonicsen_US
dc.identifier.wosnumberWOS:000526177400020en_US
dc.citation.woscount0en_US
Appears in Collections:Conferences Paper