• 更多栏目

    张硕

    • 副教授      
    • 主要任职:建筑与艺术学院党委副书记兼副院长
    • 性别:女
    • 毕业院校:大连理工大学
    • 学位:硕士
    • 所在单位:建筑与艺术学院
    • 办公地点:建筑与艺术学院305
    • 联系方式:0411-84706341
    • 电子邮箱:zhangshuo@dlut.edu.cn

    访问量:

    开通时间:..

    最后更新时间:..

    An Effective Segmentation Framework for Serialized Visible Human Slices Based on Adjacent Images Gradual Change

    点击次数:

    论文类型:期刊论文

    第一作者:Liu, Bin

    通讯作者:Zhang, BB (reprint author), Dalian Med Univ, Modern Technol & Educ Dept, Dalian 116044, Peoples R China.

    合写作者:Zhang, Bingbing,Fan, Juehui,Wang, Meng,Tian, Bo,Wang, Chao,Yan, Zhigang,Jiang, Qianfeng,Liu, Wenpeng,Zhang, Shuo

    发表时间:2016-11-01

    发表刊物:JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS

    收录刊物:SCIE、Scopus

    卷号:6

    期号:7

    页面范围:1754-1760

    ISSN号:2156-7018

    关键字:Visible Human; Color Image Segmentation; Serialized Slices; Skeleton Corner Points

    摘要:In order to obtain 3D models of the organs in Visible Human Project, in this paper, an improved sequential human body slice segmentation framework for Visible Human is proposed. Two main steps are included in this framework: First, a model based on color similarity is applied to distinguish neighboring pixels; Second, a solution on the basis of geometric feature points selecting is put forward to automatically find the seed points to segment the next slice. By this framework, color slice images of the Visible Human body can be segmented orderly with less human participation. In conclusion, the primary organs of the Visible Human can be obtained easily and precisely. Also, 3D models of these organs after 3D reconstruction are fine. Based on these 3D models obtained, many useful applications ( for example, virtual endoscopy) can be implemented. This segmentation framework can provide technical support for other related work.