科研成果详情

题名Practical Application of Intelligent Vision Measurement System Based on Deep Learning
其他题名Practical Application of Intelligent Vision Measurement System Based on Deep Learning
作者
发表日期2024-07-30
发表期刊Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation;   影响因子和分区
语种英语
原始文献类型Article
关键词blink characteristics deep learning lateral blinking detection vision fluctuation visual function
其他关键词deep learning ; lateral blinking detection ; vision fluctuation ; visual function ; blink characteristics
摘要为了全面评估临床干眼患者的真实视觉功能以及瞬目特征对人眼功能性视力的综合影响,设计开发了一种从侧面检测与分析受检者瞬目的智能视力测量系统。该系统基于深度学习关键点识别技术从侧面分析眼睑特征,对识别的上下眼睑关键点数据以折线图形式展示,并标记每次瞬目的波谷,通过基准值的设定,自动统计受检者完全瞬目与不完全瞬目的比例。结果表明,该系统性能稳定,测量准确,成功达到了预期的设计目标,可为未来的临床应用提供可靠的技术支持。. To comprehensively assess the true visual function of clinical dry eye patients and the comprehensive impact of blinking characteristics on functional vision of the human eye, an intelligent vision measurement system has been designed and developed to detect and analyze blinks from the side. The system employs deep learning keypoint recognition technology to analyze eyelid features from a lateral perspective. It presents the data of identified key points for the upper and lower eyelids in a line chart format and annotates the trough of each blink. By setting benchmark values, the system automatically calculates the proportion of complete and incomplete blinks in the tested individuals. The results indicate that the system is stable in performance and accurate in measurement, successfully achieving the anticipated design objectives. It thereby provides reliable technical support for future clinical applications.
其他摘要To comprehensively assess the true visual function of clinical dry eye patients and the comprehensive impact of blinking characteristics on functional vision of the human eye,an intelligent vision measurement system has been designed and developed to detect and analyze blinks from the side.The system employs deep learning keypoint recognition technology to analyze eyelid features from a lateral perspective.It presents the data of identified key points for the upper and lower eyelids in a line chart format and annotates the trough of each blink.By setting benchmark values,the system automatically calculates the proportion of complete and incomplete blinks in the tested individuals.The results indicate that the system is stable in performance and accurate in measurement,successfully achieving the anticipated design objectives.It thereby provides reliable technical support for future clinical applications.
资助项目Y2020919:温州市基础性医疗卫生科技项目;LTGY23H120001:浙江省自然科学基金探索公益项目
ISSN1671-7104
卷号48期号:4页码:380-384
DOI10.12455/j.issn.1671-7104.230652
页数6
收录类别SCOPUS ; 万方 ; ISTIC ; 中国科技核心期刊
URL查看原文
PubMed ID39155249
SCOPUSEID2-s2.0-85201631461
Scopus学科分类Medicine (all)
万方分类号R197.39(卫生事业管理(保健组织与事业))
引用统计
文献类型期刊论文
条目标识符https://kms.wmu.edu.cn/handle/3ETUA0LF/217600
专题眼视光学院(生物医学工程学院)、附属眼视光医院
眼视光学院(生物医学工程学院)、附属眼视光医院_白内障中心
作者单位
1.National Clinical Research Center for Ocular Diseases,Wenzhou,325027,China;
2.Eye Hospital,Wenzhou Medical University,Wenzhou,325027,China
第一作者单位眼视光学院(生物医学工程学院)、附属眼视光医院
推荐引用方式
GB/T 7714
Hu, Ruilin,Sun, Dan,Shi, Guilian,et al. Practical Application of Intelligent Vision Measurement System Based on Deep Learning[J]. Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation;,2024,48(4):380-384.
APA Hu, Ruilin, Sun, Dan, Shi, Guilian, & Pan, Anpeng. (2024). Practical Application of Intelligent Vision Measurement System Based on Deep Learning. Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation;, 48(4), 380-384.
MLA Hu, Ruilin,et al."Practical Application of Intelligent Vision Measurement System Based on Deep Learning".Zhongguo yi liao qi xie za zhi = Chinese journal of medical instrumentation; 48.4(2024):380-384.

条目包含的文件

条目无相关文件。
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Hu, Ruilin]的文章
[Sun, Dan]的文章
[Shi, Guilian]的文章
百度学术
百度学术中相似的文章
[Hu, Ruilin]的文章
[Sun, Dan]的文章
[Shi, Guilian]的文章
必应学术
必应学术中相似的文章
[Hu, Ruilin]的文章
[Sun, Dan]的文章
[Shi, Guilian]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。