勤益科大機構典藏:Item 987654321/6242
English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 2928/5721 (51%)
造访人次 : 387168      在线人数 : 153
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻


    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncut.edu.tw/handle/987654321/6242


    题名: A Statistics-Based Initial Contour Detection of Optic Disc on a Retinal Fundus Image Using Active Contour Model
    作者: 王圳木
    贡献者: 資訊工程系
    日期: 2013-01
    上传时间: 2017-10-02 09:35:24 (UTC+8)
    摘要: The retinal optic disc is the region from where the central retinal artery and optical nerve of the retina emanate. Hence, it often serves as an important landmark and reference for other features in a retinal fundus image. The features obtained from a fundus images are often helpful in the diagnosis of various eye diseases. Locating and segmenting the optic disc are key pre-processing steps for extracting retinal features. This paper proposes a statistics-based method for locating a rectangular region of interest (ROI) containing the optic disc in a retinal fundus image. From a set of candidate rectangular regions, the method chooses the ROI using statistical features, namely the mean, standard deviation, and skewness of the pixel gray levels in the candidate regions. Since an optic disc is approximately round or slightly oval in the vertical direction, this study treats the maximal inscribed circle of the ROI as the initial contour of the optic disc and uses an active contour model (ACM) to precisely segment the optic disc further based on the initial contour. The experimental results show that the proposed statistics-based method combined with an ACM provides impressive performance in the segmentation of optic discs. (15 refs)
    關聯: Journal of Medical and Biological Engineering
    显示于类别:[資訊工程系(所)] 【資訊工程系所】期刊論文

    文件中的档案:

    没有与此文件相关的档案.



    在NCUTIR中所有的数据项都受到原著作权保护.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈