|本期目录/Table of Contents|

[1]王萌.基于改进支持向量机算法的超声图像分割技术*[J].生物医学工程研究,2019,02:186-189.
 WANG Meng.Ultrasonic image segmentation based on improved support vector machine algorithm[J].Journal of Biomedical Engineering Research,2019,02:186-189.
点击复制

基于改进支持向量机算法的超声图像分割技术*(PDF)

《生物医学工程研究》[ISSN:1006-6977/CN:61-1281/TN]

期数:
2019年02期
页码:
186-189
栏目:
出版日期:
2019-06-25

文章信息/Info

Title:
Ultrasonic image segmentation based on improved support vector machine algorithm
文章编号:
1672-6278 (2019)02-0186-04
作者:
王萌
陕西能源职业技术学院,陕西 咸阳 712000
Author(s):
WANG Meng
Shanxi Energy Institute, Xianyang 712000, China
关键词:
支持向量机算法超声图像生物医学分割噪声特定区域分块特征
Keywords:
Support vector machine algorithm Ultrasonic image Biomedical SegmentationNoiseSpecific area Block feature
分类号:
R318;TP399
DOI:
10.19529/j.cnki.1672-6278.2019.02.12
文献标识码:
A
摘要:
超声图像的边缘分割受到噪声影响,基于传统支持向量机(support vector machine,SVM)超声图像分割过程存在较大缺陷。提出一种基于改进SVM算法超声图像分割算法。采用分区域特征匹配方法,进行二维超声图像的分块融合性检测和特征块匹配,根据超声纹理的规则性特征分量进行病理边缘特征提取,利用提取的精度作为约束条件,优化SVM分割过程,进行超声图像分割过程的自适应分类,实现对超声图像的快速分割。仿真结果表明,采用该方法进行超声图像分割的精度较高,对超声图像的病理特征识别能力较好,结构相似度信息较强,提高了超声图像检测和诊断分析能力。
Abstract:
The edge segmentation of ultrasound image is affected by noise. The traditional support vector machine(SVM)based ultrasound image segmentation process has some defects. An improved SVM based ultrasound image segmentation algorithm was proposed. Subregional feature matching method was used to detect and match feature blocks of two-dimensional biomedical ultrasound images. Pathological edge features were extracted according to the regular feature components of ultrasound texture. The accuracy of extraction was used as a constraint condition to optimize the SVM segmentation process. The adaptive classification of ultrasound image segmentation process was carried out to achieve fast biomedical ultrasound image segmentation.The simulation results show that the method is high precision in biomedical ultrasound image segmentation, good recognition ability in pathological feature,structural similarity information and improves the detection,diagnosis and analysis ability of biomedical ultrasound image.

参考文献/References

-

备注/Memo

备注/Memo:
(收稿日期:2018-12-25)陕西省教育厅专项资助项目(15JK1021)。Email:wm198112250@icloud.com
更新日期/Last Update: 2019-07-18