基于交叉网络的眼底视神经乳头自动定位

李居朋; 陈后金; 张新媛

doi:10.3724/SP.J.1146.2008.00232

基于交叉网络的眼底视神经乳头自动定位

doi: 10.3724/SP.J.1146.2008.00232

李居朋^{①;陈后金},
陈后金,
张新媛

基金项目:

教育部新世纪优秀人才支持计划(NO50051)和高等学校博士学科点专项科研基金(WC105002)资助课题

计量
- 文章访问数: 2935
- HTML全文浏览量: 80
- PDF下载量: 944
- 被引次数: 0
出版历程
- 收稿日期: 2008-03-04
- 修回日期: 2008-06-26
- 刊出日期: 2009-05-19

Automatic Localization of Optic Nerve Head in the Fundus Images Based on Cross-Network

摘要

摘要: 该文研究基于交叉网络的眼底视神经乳头自动定位的新方法。为描述眼底血管网络空间属性，该文提出一种新的概念交叉网络，并给出了交叉网络属性测度。依据眼底组织结构模型构建交叉网络，利用血管网络交叉密度测度，实现眼底图像视神经乳头的自动定位。采用国际通用的STARE，DRIVE眼底图像库以及临床采集图像进行不同图像质量下定位成功率测试，实验结果验证了算法的有效性。同时运算速度较已有算法也有明显提高，可以满足眼科临床检查的需求。
- 眼底图像;交叉网络;视神经乳头;自动定位
Abstract: An automatic optic nerve head localization method in the fundus images based on cross-network is studied in this paper. To describe the space properties of the retinal vessel, a new conception cross-network and measures of the network are proposed. Based on the model of fundus organs structure, automatic localization of optic nerve head is realized using the cross-networks measure parameter cross density. Experimental results verify the effectiveness of the algorithm using the STARE, DRIVE fundus image databases and the clinic images over different image qualities. And it can satisfy the requirement of clinic ophthalmological diagnosis.

HTML全文

参考文献(1)

韦企平, 童绎. 视乳头水肿. 中国实用眼科杂志, 2004, 22(10):773-777.Wei Qi-ping and Tong Yi. Optic disc edema. Chinese Journalof Practical Ophthalmology, 2004, 22(10): 773-777.[2]Siddalingaswamy P C and Prabhu G K. Automated detectionof anatomical structures in retinal images. InternationalConference on Computational Intelligence and MultimediaApplications, Sivakasi, India, Dec. 2007: 164-168.[3]Ying H J and Zhang M, et al.. Fractal-based automaticlocalization and segmentation of optic disc in retinal images.International Conference on Engineering in Medicine andBiology Society, Lyon, France, Aug. 2007: 4139-4141.[4]Thomas P K and Govindasamy V P, et al.. Locating the opticnerve in retinal images: comparing model-based and Bayesiandecision methods. International Conference on Engineering inMedicine and Biology Society, New York, USA, Aug. 2006:4436-4439.[5]Tobin K W and Chaum E, et al.. Detection of anatomicstructures in human retinal imagery. IEEE Trans. on MedicalImaging, 2007, 26(12): 1729-1739.[6]Chutatape O. Fundus foveal localization based on vesselmodel. International Conference on Engineering in Medicineand Biology Society, New York, USA, Aug. 2006: 4440-4444.[7]D'Antoni R and Giusti A. Model based retinal analysis forretinopathy detection. International Conference onEngineering in Medicine and Biology Society, Lyon, France,Aug. 2007: 6731-6734.[8]Hoover A and Goldbaum M. Locating the optic nerve in aretinal image using the fuzzy convergence of the blood vessels[J].IEEE Trans. on Medical Imaging.2003, 22(8):951-958[9]Li Jupeng and Chen Houjin. An efficient method for vesseledge detection of fundus images. International Conference onSignal Processing, Guilin, China, Nov. 2006: 2464-2467.[10]Hoover A and Kouznetsova V, et al.. Locating blood vesselsin retinal images by piecewise threshold probing of a matchedfilter response[J].IEEE Trans. on Medical Imaging.2000, 19(3):203-210[11]梁广民, 蔡学军. OPTA 算法的改进及其在指纹图像细化中的应用. 计算机工程与设计, 2006, 27(23): 4607-4609.Liang Guang-min and Cai Xue-jun. Improvement of OPTAalgorithm and its application in fingerprint images thinning.Computer Engineering and Design, 2006, 27(23): 4607-4609.

施引文献

资源附件(0)

访问统计