[1]凌朝东,陈虎,杨骁,等.结合SLIC超像素和DBSCAN聚类的眼底图像硬性渗出检测方法[J].华侨大学学报(自然科学版),2015,36(4):399-405.[doi:10.11830/ISSN.1000-5013.2015.04.0399]
　LING Chao-dong,CHEN Hu,YANG Xiao,et al.Fundus Image Hard Exudates Detection Based on SLIC Superpixels and DBSCAN Clustering[J].Journal of Huaqiao University(Natural Science),2015,36(4):399-405.[doi:10.11830/ISSN.1000-5013.2015.04.0399]
点击复制

结合SLIC超像素和DBSCAN聚类的眼底图像硬性渗出检测方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第36卷
期数:
2015年第4期
页码:
399-405
栏目:
出版日期:
2015-07-15

文章信息/Info

Title:
Fundus Image Hard Exudates Detection Based on SLIC Superpixels and DBSCAN Clustering
文章编号:
1000-5013(2015)04-0399-07
作者:
凌朝东;  陈虎;  杨骁;  张浩;  黄信
华侨大学 信息科学与工程学院, 福建 厦门 361021
Author(s):
LING Chao-dong;  CHEN Hu;  YANG Xiao;  ZHANG Hao;  HUANG Xin
College of Information Science and Engineering, Huaqiao University, Xiamen 361021, China
关键词:
图像分割;  超像素;  硬性渗出;  糖尿病视网膜病变;  简单线性迭代聚类;  基于密度的聚类算法
Keywords:
image segmentation;  superpixels;  hard exudates;  diabetic retinopathy;  simple linear iterative clustering;  density-based clustering method
分类号:
TP391.41;R774.1
DOI:
10.11830/ISSN.1000-5013.2015.04.0399
文献标志码:
A
摘要:
为自动检测出眼底图像中的硬性渗出,结合简单线性迭代聚类(SLIC)超像素分割算法和基于密度的聚类算法(DBSCAN),提出一种对眼底图像硬性渗出的检测方法.首先,采用SLIC超像素分割算法对彩色眼底图像进行过分割;然后,采用DBSCAN对上述分割得到的超像素进行聚类,形成簇;最后,分割出目标图像,并选用标准糖尿病视网膜病变数据库(DIARETDB0和DIARETDB1)的眼底图像验证上述组合算法的可行性.实验结果表明:算法能够快速、可靠地检测出眼底图像中的硬性渗出,具有可直接对彩色图像进行分割、特征提取的特点.
Abstract:
In order to detect the hard exudates in fundus images automatically, this paper presented a hard exudates detection method which combines simple linear iterative clustering(SLIC)superpixels and DBSCAN clustering algorithm to detect the Harde exudates. Firstly, an over-segmentation image was formed by algorithm of the SLIC superpixels. Next the superpixels obtained were processed using the DBSCAN method, so that the final segmentation could be generated from the clusters of superpixels. The fundus image of the standard Diabetic Retinopathy datasets of DIARETDB0 and DIARETDB1 were chosen to verify the feasibility of the method proposed. The experimental results showed that the algorithms can detect exudates effectively and reliably. Moreover, the method can be directly applied to color image segmentation and feature extraction.

参考文献/References:

[1] 贾冀.基于聚类的图像分割与配准研究[D].西安:西安电子科技大学,2013:1-2.
[2] RAM K,SIVASWAMY J.Multi-space clustering for segmentation of exudates in retinal color photographs[C]//31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society.Minneapolis:IEEE Press,2009:1437-1440.
[3] NAGY B,ANTAL B,HAJDU A.Image database clustering to improve microaneurysm detection in color fundus images[C]//25th International Symposium on Computer-Based Medical Systems.Rome:IEEE Press,2012:1-6.
[4] RANAMUKA N G,MEEGAMA R G N.Detection of hard exudates from diabetic retinopathy images using fuzzy logic[J].IET Image Processing,2013,7(2):121-130.
[5] GIANCARDO L,MERIAUDEAU F,KARNOWSKI T P,et al.Automatic retina exudates segmentation without a manually labelled training set[C]//International Symposium on Biomedical Imaging.Chicago:IEEE Press,2011:1396-1400.
[6] 刘芳,代钦,石祥滨,等.基于超像素的快速 MRF 红外行人图像分割算法[J].计算机仿真,2012,29(10):26-29.
[7] ACHANTA R,SHAJI A,SMITH K,et al.SLIC superpixels compared to state-of-the-art superpixel methods[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(11):2274-2282.
[8] 刘进立.SAR 图像分割与特征提取方法研究[D].沈阳:辽宁大学,2013:25-26.
[9] 杨静,高嘉伟,梁吉业,等.基于数据场的改进 DBSCAN 聚类算法[J].计算机科学与探索,2012,6(10):903-911.
[10] 陈刚,刘秉权,吴岩.一种基于高斯分布的自适应DBSCAN算法[J].微电子学与计算机,2013,30(3):27-30,34.
[11] 于亚飞,周爱武.一种改进的 DBSCAN 密度算法[J].计算机技术与发展,2011,21(2):30-33.
[12] 赵文,夏桂书,苟智坚,等.一种改进的DBSCAN算法[J].四川师范大学学报:自然科学版,2013,36(2):312-316.
[13] 张丽杰.具有稳定饱和度的DBSCAN算法[J].计算机应用研究,2014,31(7):1973-1975.
[14] BANDYOPADHYAY S K,PAUL T U.Segmentation of brain tumour from MRI image-analysis of K-means and DBSCAN clustering[J].International Journal of Research in Engineering and Science,2013,1(1):48-57.
[15] SAE-TANG W,CHIRACHARIT W,KUMWILAISAK W.Exudates detection in fundus image using non-uniform illumination background subtraction[C]//TENCON 2010-2010 IEEE Region 10 Conference.Fukuoka:IEEE Press,2010:204-209.
[16] 张育雄.基于几何约束和熵率的超像素分割[D].天津:天津大学,2012:30-33.
[17] LI Hui-qi,CHUTATAPE O.Automated feature extraction in color retinal images by a model based approach[J].IEEE Transactions on Biomedical Engineering,2004,51(2):246-254.
[18] WALTER T,KLEIN J C,MASSIN P,et al.A contribution of image processing to the diagnosis of diabetic retinopathy: Detection of exudates in color fundus images of the human retina[J].IEEE Transactions on Medical Imaging,2002,21(10):1236-1243.
[19] 高玮玮,沈建新,王玉亮.眼底图像中硬性渗出自动检测方法的对比[J].南京航空航天大学学报,2013,45(1):55-61.

相似文献/References:

[1]钱卫星,黄丽亚.二维Otsu自适应阈值快速算法的改进[J].华侨大学学报(自然科学版),2015,36(4):427.[doi:10.11830/ISSN.1000-5013.2015.04.0427]
　QIAN Wei-xing,HUANG Li-ya.Improvement for 2D Otsu Adaptive Threshold Fast Algorithm[J].Journal of Huaqiao University(Natural Science),2015,36(4):427.[doi:10.11830/ISSN.1000-5013.2015.04.0427]
[2]钱卫星,黄丽亚.采用二维Otsu直方图斜分快速算法实现方式的改进[J].华侨大学学报(自然科学版),2016,37(1):88.[doi:10.11830/ISSN.1000-5013.2016.01.0088]
　QIAN Weixing,HUANG Liya.Improved Implementations for 2D Otsu Histogram Fast Algorithm[J].Journal of Huaqiao University(Natural Science),2016,37(4):88.[doi:10.11830/ISSN.1000-5013.2016.01.0088]
[3]谢超,谢明红.应用局部自适应阈值方法检测圆形标志点[J].华侨大学学报(自然科学版),2016,37(2):134.[doi:10.11830/ISSN.1000-5013.2016.02.0134]
　XIE Chao,XIE Minghong.Circular Mark Point Detecting Research Based on Local Adaptive Threshold[J].Journal of Huaqiao University(Natural Science),2016,37(4):134.[doi:10.11830/ISSN.1000-5013.2016.02.0134]

备注/Memo

备注/Memo:
收稿日期: 2014-12-03
通信作者: 凌朝东(1964-),男,教授,主要从事生物医学信号处理等的研究.E-mail:edac@hqu.edu.cn.
基金项目: 国家自然科学基金资助项目(61203369, 61204122); 福建省自然科学基金资助项目(2011J01351); 福建省科技计划重点项目(2013H0029); 福建省泉州市科技计划项目(2013Z33)
更新日期/Last Update: 2015-07-20