Image segmentation using fuzzy energy-based active contour with shape prior

NCU Institutional Repository > 資訊電機學院 > 電機工程學系 > 期刊論文 > Item 987654321/107461

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://ir.lib.ncu.edu.tw/handle/987654321/107461

题名:	Image segmentation using fuzzy energy-based active contour with shape prior
作者:	徐國鎧;Tran, Thi-Thao;Pham, Van-Truong;Shyu, Kuo-Kai
贡献者:	資訊電機學院電機工程學系
关键词:	Active contour models;Energy conservation;Energy use;Fuzzy;Fuzzy energy;Fuzzy logic;Fuzzy set theory;Image segmentation;Level set method;Moment-based alignment;PCA;Shape;Shape normalization;Shape prior
日期:	2014-01-01
上传时间:	2026-04-23 14:13:43 (UTC+8)
出版者:	Academic Press Inc.;Elsevier Inc
摘要:	摘要： •A fuzzy energy-based active contour model with shape prior information for image segmentation is proposed.•The pose variation and energy minimization problems are handled without solving Euler–Lagrange equations.•The evolving shape and reference shape are aligned using a shape normalization procedure.•The reference shape could be constructed by performing the Principle Component Analysis on a set of training shapes.•The energy functional is minimized by directly calculating the fuzzy energy alterations. This paper presents a fuzzy energy-based active contour model with shape prior for image segmentation. The paper proposes a fuzzy energy functional including a data term and a shape prior term. The data term, inspired from the region-based active contour approach proposed by Chan and Vese, evolves the contour relied on image information. The shape term inspired from Chan and Zhu’s work, defined as the distance between the evolving shape and a reference one, constrains the evolving contour with respect to the reference shape. To align the shapes, we exploit the shape normalization procedure which takes into account the affine transformation. In addition, to minimize the energy functional, we utilize a direct method to calculate the energy alterations. The proposed model therefore can deal with images with background clutter and object occlusion, improves the computational speed, and avoids difficulties associated with time step selection issue in gradient descent-based approaches. 出版者： Elsevier Inc 出版日期： 2014-10-01 出處： Journal of visual communication and image representation, 2014-10, Vol.25 (7), p.1732-1745 資源來源： Elsevier ScienceDirect Journals Complete 版權： 2014 Elsevier Inc. 識別號： ISSN: 1047-3203 識別號： EISSN: 1095-9076 識別號： DOI: 10.1016/j.jvcir.2014.06.006
显示于类别:	[電機工程學系] 期刊論文

文件中的档案:

档案	描述	大小	格式	浏览次数
index.html		0Kb	HTML	19	检视/开启

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....