標題: Accessing Refractive Errors via Eccentric Infrared Photorefraction Based on Deep Learning
作者: Yang, Chia-Chi
Su, Jian-Jia
Li, Jie-En
Zhu, Zhi-Yu
Tseng, Jin-Shing
Cheng, Chu-Ming
Tien, Chung-Hao
光電工程學系
Department of Photonics
關鍵字: refractive error;photorefraction;deep learning;digital imaging processing;optical system
公開日期: 1-Jan-2019
摘要: Eccentric 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.
URI: http://dx.doi.org/10.1117/12.2542652
http://hdl.handle.net/11536/154070
ISBN: 978-1-5106-3112-0
ISSN: 0277-786X
DOI: 10.1117/12.2542652
期刊: SPIE FUTURE SENSING TECHNOLOGIES
Volume: 11197
起始頁: 0
結束頁: 0
Appears in Collections:Conferences Paper