Soft thresholding for medical image segmentation

被引：8

作者：

Aja-Fernandez, Santiago ^{[1
]}

Vegas-Sanchez-Ferrero, Gonzalo ^{[1
]}

Martin Fernandez, Miguel A. ^{[1
]}

机构：

[1] Univ Valladolid, LPI, ETSI Telecomunicac, E-47002 Valladolid, Spain

来源：

2010 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC) | 2010年

关键词：

ALGORITHM; SYSTEMS; DESIGN;

D O I：

10.1109/IEMBS.2010.5626376

中图分类号：

R318 [生物医学工程];

学科分类号：

100103 [病原生物学];

摘要：

A new soft thresholding method is presented. The method is based on relating each pixel in the image to the different regions via a membership function, rather than through hard decisions. The membership function of each of the regions is derived from the histogram of the image. As a consequence, each pixel will belong to different regions with a different level of membership. This feature is exploited through spatial processing to make the thresholding robust to noisy environments.

引用

页码：4752 / 4755

页数：4

共 19 条

[1]

A fuzzy MHT algorithm applied to text-based information tracking [J].