基于SVM的眼底图像硬性渗出检测

计算机与现代化

基于SVM的眼底图像硬性渗出检测

福州大学数字媒体研究院，福建福州350002

收稿日期:2014-02-07 出版日期:2014-04-17 发布日期:2014-04-23
作者简介:作者简介：潘燕红（1989），女，福建莆田人，福州大学数字媒体研究院硕士研究生，研究方向：图像处理与通信；潘林（1978），男，讲师，博士，研究方向：图像处理与分析。
基金资助:

基金项目：福建省自然科学基金资助项目（2012J05116）

Detection of Hard Exudates in Fundus Images Based on SVM

Research Academy of Digital Media, Fuzhou University, Fuzhou 350002, China

Received:2014-02-07 Online:2014-04-17 Published:2014-04-23

摘要/Abstract

摘要：

摘要：为克服光照不均、对比度低、软性渗出干扰等给眼底图像中硬性渗出（HEs）检测带来的困难，提出一种基于支持向量机（SVM）的检测方法。首先对眼底图像进行数学形态学结合阈值方法的粗分割，得到硬性渗出的候选区域；然后在候选区域上提取特征，并在特征提取中引入调幅调频（AMFM）特征；接着用SVM分类出HEs和非HEs。在公开的糖尿病视网膜病变图像库DIARETDB1上进行实验，结果敏感性为91.1%，特异性为94.7%。实验表明该方法可对HEs进行可靠检测。



关键词: , 糖尿病视网膜病变, 眼底图像, 硬性渗出, 支持向量机, 调幅调频

Abstract:

Abstract: To overcome the difficulties of the detection of hard exudates(HEs) such as uneven illumination, low contrast and the interference of soft exudates, a method based on SVM is proposed. Firstly we use morphological and thresholding methods to coarsely segment the candidate HEs regions in fundus images, then extract features on the candidate regions and import the AMFM features, finally we use a SVM classifier to classify the HEs and nonHEs. The experiment is based on the public diabetic retinopathy database DIARETDB1, we achieve a sensitivity of 91.1% and a specificity of 94.7%. The experimental results indicate that our method can conduct reliable detection of HEs.



Key words:

, Key words: , diabetic retinopathy； fundus images； hard exudates； SVM； AMFM

中图分类号:

TP391.41

潘燕红，潘林. 基于SVM的眼底图像硬性渗出检测[J]. 计算机与现代化.

PAN Yanhong, PAN Lin. Detection of Hard Exudates in Fundus Images Based on SVM[J]. Computer and Modernization.

参考文献

［1］

Watkins P J. ABC of diabetes: Retinopathy［J］. BMJ: British Medical Journal, 2003,326(7395):924926.

［2］ Phillips R, Forrester J, Sharp P. Automated detection and quantification of retinal exudates［J］. Graefe’s Archive for Clinical and Experimental Ophthalmology, 1993,231(2):9094.

［3］ Sinthanayothin C, Boyce J F, Cook H L, et al. Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images［J］. British Journal of Ophthalmology, 1999,83(8):902910.

［4］ 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.

［5］ Osareh A, Shadgar B, Markham R. A computationalintelligencebased approach for detection of exudates in diabetic retinopathy images［J］. IEEE Transactions on Information Technology in Biomedicine, 2009,13(4):535545.

［6］ Adarsh P, Jeyakumari D. Multiclass SVMbased automated diagnosis of diabetic retinopathy ［C］// IEEE 2013 International Conference on Communications and Signal Processing (ICCSP). 2013:206210.

［7］ Osareh A. Automated Identification of Diabetic Retinal Exudates and the Optic Disc［D］. University of Bristol, 2004.

［8］ Garcia M, Sanchez C I, Poza J, et al. Detection of hard exudates in retinal images using a radial basis function classifier［J］. Annals of Biomedical Engineering, 2009,37(7):14481463.

［9］ Havlicek J P, Harding D S, Bovik A C. The multicomponent AMFM image representation［J］. IEEE Transactions on Image Processing, 1996,5(6):10941100.

［10］Murray V, Psttichis M, Soliz P. New AMFM analysis methods for retinal image characterization［C］// IEEE 2008 the 42nd Asilomar Conference on Signals, Systems and Computers. 2008:664668.

［11］Tomi Kauppi, Valentina Kalesnykiene, JoniKristian Kamarainen, et al. DIARETDB1Standard Diabetic Retinopathy Database ［DB/OL］. http://www2.it.lut.fi/project/imageret/diaretdb1/, 20070619.

［12］British Academic Association. Retinal Photography Screening for Diabetic Eye Disease［R］. London: British Academic Association, 1997.

［13］Hsu C W, Chang C C, Lin C J. A Practical Guide to Support Vector Classification［R］. University of National Taiwan, Department of Computer Science and Information Engineering, 2003.

[1]	杨博, 庄毅. 基于AOA-MSVM的控制集群故障检测方法[J]. 计算机与现代化, 2023, 0(12): 112-116.
[2]	杨孙哲, 孙爱珍. 基于HSV颜色与LBP纹理特征的水稻氮素营养诊断[J]. 计算机与现代化, 2023, 0(07): 86-92.
[3]	申志, 李元 . 基于KPCA和SSA优化SVM的非线性过程故障检测#br#[J]. 计算机与现代化, 2023, 0(06): 15-20.
[4]	尹建丰, 卫鑫, 顾雄伟, 黄凯, 魏敏捷. 基于图像阈值优化及改进SVM的电表数字识别[J]. 计算机与现代化, 2023, 0(05): 106-110.
[5]	李静元, 张珂, 杨东裕. 基于雾计算的工业互联网安全数据访问方法[J]. 计算机与现代化, 2022, 0(12): 118-122.
[6]	丁婉莹, 陈伟, 李昭慧. 基于编解码结构的多特征融合眼底图像分割[J]. 计算机与现代化, 2022, 0(07): 1-7.
[7]	赵延平, 王芳, 夏杨. 基于支持向量机的短文本分类方法[J]. 计算机与现代化, 2022, 0(02): 92-96.
[8]	赵聪慧, 冯庆胜. 基于DT-CWT和SVM的踏面旋转不变纹理提取算法[J]. 计算机与现代化, 2021, 0(12): 85-90.
[9]	陈春燕, 刘梦赤. 基于粒子群遗传算法的智能组卷策略[J]. 计算机与现代化, 2021, 0(08): 16-23.
[10]	陈翔, 邹庆年, 谢绍宇, 陈翠琼. 基于迁移学习策略的压板开关状态识别[J]. 计算机与现代化, 2021, 0(05): 120-126.
[11]	宋鑫, 樊志强, . 基于Laguerre 前向神经网络的信息服务性能建模方法 [J]. 计算机与现代化, 2021, 0(03): 1-6.
[12]	魏健, 赵红涛, 刘敦楠, 加鹤萍 . 基于集成模型的超短时负荷预测方法[J]. 计算机与现代化, 2021, 0(03): 12-17.
[13]	王文蔚, 肖军弼, 程鹏, 张悦. 基于SDN的DDoS攻击防御系统[J]. 计算机与现代化, 2021, 0(02): 117-121.
[14]	张文华，张志俊. 基于SVM的新能源公交车运营里程核查方法[J]. 计算机与现代化, 2020, 0(05): 39-.
[15]	郑沫利1,赵艳轲1,闫敏2,孙俊2,刘雍容1. 基于RDPSO-SVM的粮食产后储藏环节损耗智能评估方法[J]. 计算机与现代化, 2020, 0(03): 72-.