视网膜血管图像处理的若干关键问题研究
|
摘要
眼底视网膜血管是人体唯一可非创伤性直接观察的较深层次的微血管,其形态结构的变化与高血压、糖尿病、动脉硬化等心血管疾病的病程、严重程度及愈后情况密切相关。因此,利用图像处理的方法对视网膜血管图像的相关参数进行定性和定量分析,对眼科医学研究的深入开展、疾病的早期诊断和分析以及对以往人工无力进入的区域的研究均具有重要意义。此外,视网膜血管形态结构具有唯一性,与其他生物特征相比具有更高的保密性和防伪能力,可以作为生物特征进行个人身份识别。
本文首先简要介绍了视网膜血管图像的研究意义及研究现状,然后针对视网膜图像处理中的一些关键技术进行了较为深入的研究,提出了一些新的思想和算法。本文的主要工作和贡献如下:
1)研究了基于灰度图像的血管直径测量及其在分叉角测量中的应用。对视网膜血管图像的几何形态结构进行了分析,根据视网膜血管横截面灰度高斯模型,提出一种基于灰度图像的管径自动测量方法。与以往方法相比该方法不需要对目标血管进行二值化操作,直接根据血管横截面灰度模型对ROI区域分别进行行操作和列操作找到中心点的粗略位置,然后借助Hessian矩阵的特征向量来确定血管的径向方向,利用最小二乘拟合径向的灰度值,多次重复直到中心点收敛,最后通过找出的拐点来确定血管的直径。为提高算法的鲁棒性,采用了五个相邻的直径的加权平均作为待测点的直径。另外,根据血管内血液流动的动力学原理来定义血管的分叉角度,把测得的直径应用到分叉角度测量上,实验结果显示该方法稳定、有效。
2)基于眼底视网膜血管的分布结构及视盘本身的特点,提出一种快速自动定位视盘的方法。首先根据视网膜血管的网络分布结构大致定位视盘的垂直坐标;然后根据视盘的亮度信息及视盘与血管的关系来定位视盘的水平坐标;最后把视盘限定在以粗定位的坐标点为中心的一个小窗口内,用Hough变换精确定位视盘中心。该方法不需要事先分割视网膜血管,也不需要对算法进行训练。实验结果表明,文中算法具有较高的定位精度和较快的定位速度。
3)研究了视网膜血管节点(分叉点和交叉点)的提取和分类方法。由动静脉血管组成的眼底视网膜血管结构的节点是预测心血管疾病、图像分析和生物学应用的重要特征,把角点检测引入到视网膜血管分叉点和交叉点的自动提取和分类中。首先对二值化的血管图像进行边缘检测,然后采用基于点到弦的距离累加(CPDA)的角点检测方法得到候选特征点,再根据视网膜血管图像的拓扑结构设计自适应矩形探测器对候选特征点进行删减和分类。试验结果表明,基于CPDA的角点检测和自适应矩形探测器的方法有效的实现了节点的提取和分类。
4)针对眼底图像获取过程中眼球转动的问题,提出一种基于节点最近邻结构的具有旋转、平移不变性的视网膜血管形态识别方法。该方法首先利用节点的周边结构稳定性的特点来进行节点结构特征提取,然后进行图像相关结构匹配的判定。实验结果证明了该识别算法的有效性和可靠性,正确识别率达到98.57%。
Blood vessels in the eye are the only deeper microvascular which can be directly non-invasive observed, the morphological changes in the structure are closely related to the duration, severity and after cure of high blood pressure, diabetes, arteriosclerosis and other cardiovascular disease. Therefore, using the method of image processing to qualitative and quantitative analysis the parameters of retinal blood vessels, which is significant to ophthalmic medical research, early disease diagnosis and the research on the region which formerly incapable entered. In addition, retinal vascular can serve as a biometric for personal identification for its morphology is unique, and has high level security and anti-forge capability compared with other biological characteristics.
This article briefly describes the significance of retinal blood vessels and the research status, and then some key technical problems of retinal image processing and analysis have been studied. At the same time, some new idea and algorithm are proposed. The main work and contributions of this thesis are as follows:
1) The method of vessel diameter and bifurcation angle quantification based on gray image is proposed. According to Gaussian model of retinal blood vessel profile, a retinal vessel blood diameter automatic measurement method is proposed based on the gray-scale image. This method does not need segment and binary operation, it directly finds the rough location of the center points of ROI region, which is operated in column and row respectively, and then using the eigenvectors of Hessian matrix to determine the blood vessels radial direction, at last fitting its radial gray values with least-squares. The process is repeated until the central point convergence. Finally the diameter of blood vessel is determined by finding the knee point. To enhance the robustness of the algorithm, the weighted average of five adjacent diameters are used to replace the diameter of the test points. Also, according to vascular blood flow dynamics to define the vascular bifurcation angle, the measured diameter applied to the bifurcation angle measurement, the experimental results show that the method is stable and effective.
2) Based on the structure of retinal blood vessels and the features of the optic disc (OD), a fast automatic method of optic disc localization is proposed. In this method, the vertical coordinate of the OD is determined firstly according to the distribution structure of the retinal blood vessel network. Then, the horizontal coordinate is located based on the OD brightness information and the relationship between the OD and the blood vessels. Finally, the OD is limited in a small window with the rough location of the OD as the center, and the OD center is precisely positioned via the Hough transform. By this method, neither priorly segmentation of retinal blood vessels nor algorithm training is required. Experimental results indicate that the proposed method is of high localization accuracy and speed.
3) Retinal vascular bifurcations and crossovers points extraction and classification methods are studied in the thesis. The feature points of the arteriovenous retinal vascular are important landmarks in predicting cardiovascular disease, image analysis and as biometrics application. Corner detection method is introduced to extract the vascular bifurcations and crossovers points from eye fundus images. First, the edge detection operator is used to get the binary edge image. And then, a corner detection method based on chord-to-point distance accumulation (CPDA) technique is applied to obtain the candidate feature points. According to the topological structure of vessel, the adaptive rectangular detector is designed to class candidate points. The results show that the method based on CPDA and adaptive rectangular detector is feasible to detect and classify the feature points.
4) In order to overcome the effects of eye movement during the funds image acquisition stage, a method based on the node’s adjacent structure for pattern recognition of retinal blood vessels was proposed. The method has the quality of rotation and translation invariance. Firstly, the node structure characteristics are extracted using the structural stability of the surrounding nodes, and then matching the image correlation structure. Experimental results on a database demonstrated the effectiveness and reliability of the recognition algorithm. The accuracy rate of 98.57% is reached for the proposed system.
本文首先简要介绍了视网膜血管图像的研究意义及研究现状,然后针对视网膜图像处理中的一些关键技术进行了较为深入的研究,提出了一些新的思想和算法。本文的主要工作和贡献如下:
1)研究了基于灰度图像的血管直径测量及其在分叉角测量中的应用。对视网膜血管图像的几何形态结构进行了分析,根据视网膜血管横截面灰度高斯模型,提出一种基于灰度图像的管径自动测量方法。与以往方法相比该方法不需要对目标血管进行二值化操作,直接根据血管横截面灰度模型对ROI区域分别进行行操作和列操作找到中心点的粗略位置,然后借助Hessian矩阵的特征向量来确定血管的径向方向,利用最小二乘拟合径向的灰度值,多次重复直到中心点收敛,最后通过找出的拐点来确定血管的直径。为提高算法的鲁棒性,采用了五个相邻的直径的加权平均作为待测点的直径。另外,根据血管内血液流动的动力学原理来定义血管的分叉角度,把测得的直径应用到分叉角度测量上,实验结果显示该方法稳定、有效。
2)基于眼底视网膜血管的分布结构及视盘本身的特点,提出一种快速自动定位视盘的方法。首先根据视网膜血管的网络分布结构大致定位视盘的垂直坐标;然后根据视盘的亮度信息及视盘与血管的关系来定位视盘的水平坐标;最后把视盘限定在以粗定位的坐标点为中心的一个小窗口内,用Hough变换精确定位视盘中心。该方法不需要事先分割视网膜血管,也不需要对算法进行训练。实验结果表明,文中算法具有较高的定位精度和较快的定位速度。
3)研究了视网膜血管节点(分叉点和交叉点)的提取和分类方法。由动静脉血管组成的眼底视网膜血管结构的节点是预测心血管疾病、图像分析和生物学应用的重要特征,把角点检测引入到视网膜血管分叉点和交叉点的自动提取和分类中。首先对二值化的血管图像进行边缘检测,然后采用基于点到弦的距离累加(CPDA)的角点检测方法得到候选特征点,再根据视网膜血管图像的拓扑结构设计自适应矩形探测器对候选特征点进行删减和分类。试验结果表明,基于CPDA的角点检测和自适应矩形探测器的方法有效的实现了节点的提取和分类。
4)针对眼底图像获取过程中眼球转动的问题,提出一种基于节点最近邻结构的具有旋转、平移不变性的视网膜血管形态识别方法。该方法首先利用节点的周边结构稳定性的特点来进行节点结构特征提取,然后进行图像相关结构匹配的判定。实验结果证明了该识别算法的有效性和可靠性,正确识别率达到98.57%。
Blood vessels in the eye are the only deeper microvascular which can be directly non-invasive observed, the morphological changes in the structure are closely related to the duration, severity and after cure of high blood pressure, diabetes, arteriosclerosis and other cardiovascular disease. Therefore, using the method of image processing to qualitative and quantitative analysis the parameters of retinal blood vessels, which is significant to ophthalmic medical research, early disease diagnosis and the research on the region which formerly incapable entered. In addition, retinal vascular can serve as a biometric for personal identification for its morphology is unique, and has high level security and anti-forge capability compared with other biological characteristics.
This article briefly describes the significance of retinal blood vessels and the research status, and then some key technical problems of retinal image processing and analysis have been studied. At the same time, some new idea and algorithm are proposed. The main work and contributions of this thesis are as follows:
1) The method of vessel diameter and bifurcation angle quantification based on gray image is proposed. According to Gaussian model of retinal blood vessel profile, a retinal vessel blood diameter automatic measurement method is proposed based on the gray-scale image. This method does not need segment and binary operation, it directly finds the rough location of the center points of ROI region, which is operated in column and row respectively, and then using the eigenvectors of Hessian matrix to determine the blood vessels radial direction, at last fitting its radial gray values with least-squares. The process is repeated until the central point convergence. Finally the diameter of blood vessel is determined by finding the knee point. To enhance the robustness of the algorithm, the weighted average of five adjacent diameters are used to replace the diameter of the test points. Also, according to vascular blood flow dynamics to define the vascular bifurcation angle, the measured diameter applied to the bifurcation angle measurement, the experimental results show that the method is stable and effective.
2) Based on the structure of retinal blood vessels and the features of the optic disc (OD), a fast automatic method of optic disc localization is proposed. In this method, the vertical coordinate of the OD is determined firstly according to the distribution structure of the retinal blood vessel network. Then, the horizontal coordinate is located based on the OD brightness information and the relationship between the OD and the blood vessels. Finally, the OD is limited in a small window with the rough location of the OD as the center, and the OD center is precisely positioned via the Hough transform. By this method, neither priorly segmentation of retinal blood vessels nor algorithm training is required. Experimental results indicate that the proposed method is of high localization accuracy and speed.
3) Retinal vascular bifurcations and crossovers points extraction and classification methods are studied in the thesis. The feature points of the arteriovenous retinal vascular are important landmarks in predicting cardiovascular disease, image analysis and as biometrics application. Corner detection method is introduced to extract the vascular bifurcations and crossovers points from eye fundus images. First, the edge detection operator is used to get the binary edge image. And then, a corner detection method based on chord-to-point distance accumulation (CPDA) technique is applied to obtain the candidate feature points. According to the topological structure of vessel, the adaptive rectangular detector is designed to class candidate points. The results show that the method based on CPDA and adaptive rectangular detector is feasible to detect and classify the feature points.
4) In order to overcome the effects of eye movement during the funds image acquisition stage, a method based on the node’s adjacent structure for pattern recognition of retinal blood vessels was proposed. The method has the quality of rotation and translation invariance. Firstly, the node structure characteristics are extracted using the structural stability of the surrounding nodes, and then matching the image correlation structure. Experimental results on a database demonstrated the effectiveness and reliability of the recognition algorithm. The accuracy rate of 98.57% is reached for the proposed system.
引文
[1]张雪平.原发性高血压相关因素与中医证型对视网膜血管管径的影响[D].广州中医药大学硕士论文, 2007:3-6.
[2]周钢,陈瑛,程建新等.糖尿病性视网膜血管管径改变[J].中国实用眼科杂志, 2005,23(3):238.
[3]林土胜,徐锦堂,梁庆源.视网膜血管管径量化及对眼底血管病变的应用价值[J].暨南大学学报(自然科学与医学版), 1999,20(2):33-36.
[4] Tascini G., Passerni G., Puliti P., et al. Retina Vascular Network Recognition [A]. Proceedings of the International Society for Optical Engineering [C]. Newport Beach: Society of Photo-Optical Instrumentation Engineers, 1993:322-329.
[5]闵鹊秋.高血压病视网膜病变[J].实用医院临床杂志, 2004,1(1):11.
[6] Chatterjee S., Chattopadhya S., Hope-Ross M., et al. Hypertension and the eye: Changing perspectives [J]. Journal of Human Hypertension, 2002, 16(10):667-675.
[7] Wong T. Y., Mitchell P. The eye in hypertension [J]. The Lancet, 2007, 369(9559):425-435.
[8] Klonoff D. C., Schwartz D. M. An economic analysis of interventions for diabetes [J]. Diabetes Care, 2000, 23(3):390-404.
[9]王爽.视网膜微血管异常与心脑血管健康评估[J].眼科, 2007, 16(z1):43.
[10] Chaudhuri S., Chatterjee S., Katz N., et al. Detection of blood vessels in retinal images using two-dimensional matched filters [J]. IEEE Transactions on Medical Imaging, 1989, 8(3):263-269.
[11] Sun Y. Automated identification of vessel contours in coronary arteriogram by an adaptive tracking algorithm [J]. IEEE Transactions on Medical Imaging, 1989, 8(1):78-88.
[12] Tolias Y. A., Panas S. M. A fuzzy vessel tracking algorithm for retinal images based Oil fuzzy clustering [J]. IEEE Transactions on Medical Imaging, 1998, 17(2):263-273.
[13] Hoover A., Kouznetsova V., Goldbaum M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response [J]. IEEE Transactions on Medical Imaging, 2000, 19(3):203-210.
[14] Jiang X. Y., Mojon D. Adaptive local shareholding by verification-basedmulti-threshold probing with application to vessel detection in retinal images [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(1):131-137.
[15]林土胜,秦华标,赖声礼.基于拆支跟踪法提取特征的视网膜血管形态识别[J].华南理工大学学报(自然科学版), 2000,28(5):54-58.
[16]朱宏擎.基于灰度-梯度共生矩阵的视网膜血管分割方法[J].上海交通大学学报, 2004,38(9):1485-1488.
[17]张恒义,蒋黔麟,虞亚军等.基于视网膜血管模型的图像分割与血管提取[J].电子学报, 1999,27(6):65-67.
[18]许雷,郑筱祥,俞锋等.基于眼底视网膜血管网络模型的血管提取方法[J].浙江大学学报(工学版), 1999,33(4):386-392.
[19]仇恒志,钟鼎苏.一种视网膜血管的分割方法[J].江西医学院学报, 2009,49(1):129-133.
[20]汤敏,王惠南.彩色视网膜血管图像的自动分割算法[J].仪器仪表学报, 2007,28(7):1281-1284.
[21]姚畅,陈后金.一种新的视网膜血管网络自动分割方法[J].光电子.激光, 2009,20(2):274-278.
[22] Wong T. Y., Klein R. Retinal arteriolar narrowing and risk of diabetes mellitus in middle-aged persons [J]. JAMA, 2002, 287(19):2528-2533.
[23] Klein R.,Klein B. E., Moss S. E., et al. Retinal vascular abnormalities in persons with typeⅠdiabetes [J]. The Wisconsin Epidemiologic Study of Diabetic Retinopathy: XVIII. Ophthalmology, 2003, 110:2118-2125.
[24]郭倩茹.视网膜微血管直径测量及与糖尿病关系的研究现状[J].中国煤炭工业医学杂志,2008,11(12):1982-1983.
[25]林土胜,杜明辉,徐锦堂.视网膜血管高血压交叉压迫征的量化研究[J].生物医学工程杂志, 2001,18(3):397-399.
[26] Qingyuan Liang, David Wong, Alan Berger, et al. Annular Vein Narrowing: a Possible Risk Factor in Branch Retinal Vein Occlusion with Different Artery-vein Patterns of Arteriovenous Crossings[C]. ASRS (American Society of Retinal Specialists) 28th Annual Meeting. August 2010, Vancouver, British Columbia, Canada.
[27]曹文轩.视网膜血管测量计[J].中华眼科杂志,1964, 11(1):67.
[28] Donoso L. A., Magargal L. E., Sanborn G., et al. Microcomputer application in retinal research [J]. Ophthalmology, 1982, 89(1): 81-85.
[29] Carsten S. Extracting Curvilinear Structures: A Differential Geometric Approach [A]. Proceedings of the 4th European Conference on Computer Vision [C]. Cambridge: Springer, 1996: 630-641.
[30] Yoshinobu S., Takahiro A., Masayuki H., et al. A viewpoint determination system for stenosis diagnosis and quantification in coronary angiographic image acquisition [J]. IEEE Transactions on Medical Imaging, 1998, 17(1): 121-137.
[31] James L., Andrew H., David S., et al. Measurement of retinal vessel widths from fundus images based on 2-D modeling [J]. IEEE Transactions on Medical Imaging, 2004, 23(10): 1196-1204.
[32] Thomas K., Guido G., Gabor S., et al. Multiscale detection of curvilinear structures in 2-D and 3-D image data [A]. Proceedings of International Conference on Computer Vision [C]. Los Alamitos: IEEE CS, 1995: 864-869.
[33] Chanussot J., Lambert P. An application of mathematical morphology to road network extraction on SAR images [A]. Proceeding of the International Symposium on Mathematic Morphology [C], Amsterdam: 1998:399-406.
[34] Zhao X. F., Duan W. W., Lin T.H., et al. A method of retinal vessel width measurement [A]. Proceedings of 2nd International Conference on Computer and Automation Engineering [C]. Singapore: IEEE CS, 2010, 443-446.
[35]廖勇军.视网膜图像处理关键技术研究[D].重庆大学硕士学位论文,2008,10.
[36] Yannis A. T., Stavros M. P. A fuzzy vessel tracing algorithm for retinal images based on fuzzy clustering [J]. IEEE Transactions on Medical Imaging, 1998, 17(2): 263-273.
[37] Liu I. and Sun Y. Recursive tracking of vascular networks in angiograms based on the detection and deletion scheme [J]. IEEE Transactions on Medical Imaging, 1993, 12(2): 334-341.
[38] Kostas H., Serafim N. E., Nicos M.,et al. Model-based morphological segmentation and labeling of coronary angiograms [J]. IEEE Transactions on Medical Imaging, 1999, 18(10): 1003-1015.
[39]陆建荣,斯海臣,郁道银.冠状动脉血管直径测量方法的研究[J].中国生物医学工程学报, 2005,24(4):510-512.
[40]林土胜,秦华标,赖声礼.视网膜血管可逆量化的方法与实现[J].华南理工大学学报(自然科学版), 1999,27(7):27-31.
[41] Aylward S. R., Bullitt E. Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction [J]. IEEE Transactions on MedicalImaging, 2002, 21(2):61-75.
[42] Al-Diri B., Hunter A., Steel D. An active contour model for segmenting and measuring retinal vessels [J]. IEEE Transactions on Medical Imaging, 2009, 28(9):1488-1496.
[43] Zhou L., Rzeszotarski M. S., Singerman L. J., et al. The detection and quantification of retinopathy using digital angiograms [J]. IEEE Transactions actions on Medical Imaging, 1994, 13(4): 619-626.
[44] Gang L., Chutatape O., Krishnan M. Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter [J]. IEEE Transactions on Medical Imaging, 2002, 49(2): 168-172.
[45] Lowell J., Hunter A., Steel D., et al. Measurement of retinal vessel widths from fundus images based on 2-D modeling [J]. IEEE Transactions on Medical Imaging, 2004, 23(10): 1196-1204.
[46]姚畅,陈后金.一种基于先验知识的视网膜血管宽度测量方法[J].中国科技论文在线, 2009,4(1):64-68.
[47]姚畅,陈后金,李居朋.基于过渡区提取的视网膜血管分割方法[J].电子学报, 2008, 36(5): 974-978.
[48]贾冬焱,郝立巍等.自动测量造影图像中血管中心线和宽度的新方法[J].中国生物医学工程学报, 2007,26(2):214-219.
[49]刘国才,王耀南,全惠敏.基于多层Mumford-Shah向量模型的彩色视乳头图像杯盘重建、分割与度量[J].中国生物医学工程学报, 2007,26(5):700-707.
[50] Hoover A., Goldbaum M. Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels [J]. IEEE Transactions on Medical Imaging, 2003, 22(8):951-958.
[51] Foracchia M., Grisan E., Ruggeri A. Detection of optic disc in retinal images by means of a geometrical model of vessel structure [J]. IEEE Transactions on Medical Imaging, 2004, 23(10):1189-1195.
[52] Sinthanayothin C., Boyce J. F., Cook H. L., et al. Automated localization of the optic disc, fovea, and retinal blood vessels from digital color fundus images [J]. British Journal of Ophthalmol, 1999, 83(8): 902-910.
[53] Barrett S., Naess E., Molvik T. Employing the Hough Transform to locate the optic disk [J]. Biomedical Sciences Instrumentation, 2001, 37(2):81-86.
[54] LI H., Opas C. Automatic location of optic disk in retinal images [A]. Proceedings of the International Conference on Image Processing [C]. Thessalonik: IEEE CS,2001:837-840.
[55] Walter T., Klein J. C., Massin P., et al. A contribution of mage 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.
[56] Youssif A., Ghalwash A., Ghoneim A. Optic disc detection from normalized digital fundus images by means of a vessels’direction matched filter [J]. IEEE Transaction on Medical Imaging, 2008, 27(1):11-18.
[57] Mahfouz A. E., Fahmy A. S. Ultrafast localization of the optic disc using dimensionality reduction of the search space [A]. Proceedings of the 12th International Conference on Medical Image Computing and Computer Assisted Intervention [C]. London: IEEE, 2009: 985-992.
[58] Robin G. D., Paik D. S., Johnston P. C., et al. Measurements of the aorta and its branches with helical CT [J]. Radiology, 1999,206 (3):823-829.
[59] Parida L., Geiger D., Hummel R. Junctions: Detection, classification, and reconstruction [J]. IEEE Transactions Pattern Analysis and Machine Intelligence, 1998, 20(7): 687-698.
[60] Tsai C. L., Stewart C. V., Tanenbaum H. L., et al. Model-based method for improving the accuracy and repeatability of estimating vascular bifurcations and crossovers from retinal fundus images [J]. IEEE Transactions on information Technology in Biomedicine, 2004, 8(2):122-129.
[61] Perez M. E., Highes A. D., Stanton A. V., et al. Retinal vascular tree morphology: a semi-automatic quantification [J]. IEEE Transactions on Biomedical Engineering, 2002, 49(8):912-917.
[62] Bevilacqua V. S., CambóL., Cariello G., et al. A combined method to detect retinal fundus features [A]. Proceedings of the European Conference on Emergent Aspects in Clinical Data Analysis [C]. Pisa: 2005.
[63]林土胜.视网膜血管形态识别与血管管径量化的研究[D].华南理工大学博士论文,2000,1.
[64] Calvo D., Ortega M., Penedo M. G., et al. Automatic detection and characterisation of retinal vessel tree bifurcations and crossovers in eye fundus images [J]. Computer Methods and Programs in Biomedicine, (2010), article in press
[65] Mari?o C., Penedo M. G., Penas M., et al. Personal authentication using digital retinal images [J]. Pattern Analysis and Applications, 2006, 9(1):21-33.
[66] Rahman N. A., Mohamed A. S., Rasmy M. E. Retinal identification [A]. Proceedings of International Biomedical Engineering Conference [C]. Cairo: IEEE CS, 2008.
[67] Ortega M., Penedo M. G., Rouco J., et al. Retinal verification using a feature points-based biometric pattern [J]. Eurasip Journal on Advances in Signal Processing, 2009, 2009(2009).
[68] Tan X. J., Bhanu B. A robust two step approach for fingerprint identification [J]. Pattern Recognition Letter, 2003, 24(13):2127-2134.
[69]李海英.眼底血管的识别和对比研究[D].吉林大学硕士学位论文,2006,12.
[70] Latha L., Pabitha M., Thangasamy S. A novel method for person authentication using retinal images [A]. Proceedings of International Conference on Innovative Computing Technologies [C]. Karur-Tamilnadu: IEEE CS, 2010.
[71] http://www.xshospital.com/info/detail/1996.html
[72] Haar F. Automatic localization of the optic disc in digital colour imges of the human retinal [D]. Master's thesis, Netherlands: Utrecht University, 2005.
[73] Hoover A. and Goldbaum M. Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels [J]. IEEE Transactions Medical Imaging, 2003, 22 (8):951–958.
[74] Pratt W. K. Digital image processing [M]. 2nd Edition, Wiley.
[75]刘祝华.图像去噪方法的研究[D].江西师范大学硕士学位论文,2005,5.
[76]张莹,王耀南.基于Gabor滤波器包络的人脸识别算法[J].中国图象图形学报, 2008,13(12):2314-2320.
[77]曹江中,戴青云,何家峰等.基于纹理分布和Gabor滤波器的虹膜识别算法[J].计算机工程,2006,32(9):199-200.
[78] Daugman J. G. Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression [J]. IEEE Transaction on Acoustics, Speech and Signal Processing, 1988, 36(7):1169-1179.
[79]刘尚平,陈骥.基于Gabor滤波与数学形态学的视网膜图像增强方法[J].光电子.激光,2010,21(2):318-322.
[80]索爱黎.形态学图像分析:原理与应用[M].王小鹏,译.北京:清华大学出版社,2008: 62-65.
[81]张立国,杨瑾,李晶等.基于小波包和数学形态学结合的图像特征提取方法[J].仪器仪表学报,2010,31(10):2285-2289.
[82] Naegel B. Using mathematical morphology for the anatomical labeling of vertebrae from 3D CT-scan images [J]. Computerized Medical Imaging and Graphics, 2007, 31(3): 141-156.
[83]王慧锋,战桂礼,罗晓明.基于数学形态学的边缘检测算法研究及应用[J].计算机工程与应用,2009, 31(2):223-226.
[84]王艳芬.视网膜血管灰度图像血管检测方法的研究[D].华南理工大学硕士学位论文,2006.6.
[85] Otsu N. A threshold selection method form gray-level histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.
[86] Gonzalez R. C., Woods R.E., Eddins S.L. Digital Image Processing Using Matlab [M].阮秋琦.北京:电子工业出版社, 2005:348-349.
[87]刘轩,刘佳宾.基于对比度受限自适应直方图均衡的乳腺图像增强[J].计算机工程与应用,2008,44(10):173-175.
[88] Canny J. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(6): 679-698.
[89] Stanton A. V., Mullaney P. A method of quantifying retinal microvascular alterations associated with blood pressure and age [J]. Journal of Hypertension, 1995, 13:41-48.
[90]许燕,胡广书等.基于Hessian矩阵的冠状动脉中心线的跟踪算法[J].清华大学学报(自然科学版), 2007,47(6):889-892.
[91] Lakemond R., Fookes C., Sridharan S. Affine adaptation of local image features using the hessian matrix [J]. Advanced Video and Signal Based Surveillance, 2009:496-501.
[92]乔立山,王玉兰,曾锦光.实验数据处理中曲线拟合方法[J].成都理工大学学报, 2004,31(1):91-95.
[93] Gregory E., Fasshauer. Toward approximate moving least squares approximation with irregularly spaced centers [J]. Computer Methods in Applied Mechanics and Engineering, 2004, 193(12):1231-1243.
[94]张淮清,俞集辉.线路电磁场测量数据的移动最小二乘拟合处理[J].高电压技术,2010,36(3):661-665.
[95] Qingyuan Liang, David Wong. Vein compression and angle pattern of arteriovenous crossing in branch retinal vein occlusion[C]. COS (Canadian Ophthalmological Society) 2009 annual meeting. June 2009, Toronto, Ontario, Canada.
[96] Staal J. J., Abramoff M. D., Niemeijer M., et al. Ridge based vessel segmentation incolor images of the retina [J]. IEEE Transactions on Medical Imaging, 2004, 23(4):501-509.
[97]张恒义,虞亚军等.计算机眼底血管图像分析诊断系统[J].生物医学工程学杂志, 1999,16(2):198-202.
[98] Qingyuan Liang, David Wong. The Roles of Artery-vein Relation of an Arteriovenous Crossing and Vein Bifurcation in Branch Retinal Vein Occlusion[C]. WOC (World Ophthalmology Congress) 2010, XXXII International Congress of Ophthalmology, 108th DOG Congress, June 2010, Berlin, Germany.
[99]黄叔仁,张晓峰.眼底病诊断与治疗[M].北京:人民卫生出版社,2003.2:230-237.
[100]刁颖敏.生物力学的原理与应用[M].上海:同济医科大学出版社,1991:160-167.
[101]郭萍,谢琪,刘礼恩.分支血管之间的夹角[J].中国现代医学杂志, 1999, 9(7): 35-36.
[102] Gagnon L., Lalonde M., Beaulieu M., et al. Procedure to detect anatomical structures in optical funds images [J]. IEEE Transactions on Medical Imaging, 2001:1218–1225.
[103] Li H., Chutatape O. A model-based approach for automated feature extraction in fundus images [A]. Proceedings of the 9th International Conference on Computer Vision [C], Beijing: IEEE, 2003: 394-399.
[104] Abramoff M. D., Niemeijer M., Suttorp-Schulten M. S. A., et al. Evaluation of a system for automatic detection of diabetic retinopathy from color fundus photographs in a large population of patients with diabetes [J]. Diabetes Care, 2008, 31(2):193–198.
[105]赵晓芳,林土胜,李碧.视网膜图像中视盘的快速自动定位方法[J].华南理工大学学报(自然科学版), 2011,39(2):71-75.
[106] Zhu X. L., Rangaraj M. Detection of the optic disc in images of the retina using the Hough transform [A]. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society [C]. Alberta: IEEE, 2008:3546-3549.
[107] Thanapong C., Sarat Y., Sun Z. H., et al. Edge detection of the optic disc in retinal images based on identification of a round shape [A]. Proceedings of the International Symposium on Communications and Information Technologies [C]. Laos: IEEE, 2008: 670-674.
[108] Thongnuch V., Uyyanonvara B. Automatic detection of optic disc from fundus images of ROP infant using 2D circular Hough transform [A]. Proceedings of the 2nd International Symposium on Biomedical Engineering [C]. Bangkok: IEEE, 2006: 328- 330.
[109]冯国进,顾国华,张保民.指纹图像预处理与特征提取[J].计算机应用研究,2004 (5):183-185.
[110] Wang L., Bhalerao A., Wilson R. Analysis of retinal vasculature using a multiresultion hermite model [J]. IEEE Transactions on Medical Imaging, 2007, 26(2):137-152.
[111] Soares J. V. B., Leandro J. J. G., Cesar R. M., et al. Retinal vessel segmentation using the 2-D gabor wavelet and supervised classification [J]. IEEE Transactions on Medical Imaging, 2006, 25(9):1214-1222.
[112] Lam B. S. Y. and Yan H. A Novel Vessel Segmentation Algorithm for Pathological Retina Images Based on the Divergence of Vector Fields [J]. IEEE Transactions on Medical Imaging, 2008, 27(2): 237-245.
[113] Sofka M., Stewart C. V. Retinal vessel centerline extraction using multiscale matched filters, confidence and edge measures [J]. IEEE Transactions on Medical Imaging, 2006, 25(12):1531-1546.
[114] Bhuiyan A., Nath B., Chua J., et al. Automatic detection of vascular bifurcations and crossovers from color retinal fundus images [A]. Proceedings of the 3rd International Conference on Signal-Image Technologies and Internet-Based Systems [C]. ShangHai: IEEE CS, 2007:711-718.
[115] Mokhtarian F., Suomela R. Robust image corner detection through curvature scale space [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(12):1376-1378.
[116]孙君顶,郭启强.张兆生基于曲率尺度空间的轮廓角点检测[J].光电工程,2009,36(7):78-82
[117] Han J. H., Poston T. T. Chord-to-point distance accumulation and planar curvature: A new approach to discrete curvature [J]. Pattern Recognition Letters, 2001, 22: 1133-1144.
[118] Awrangjeb M., Lu G. J. Robust image coner detection based on the chord-to-point distance accumulation technique [J]. IEEE Transactions on multimedia, 2008, 10(6):1059-1072.
[119] Zhang X., Lei M., Yang D., et al. Multi-scale curvature product for robust image corner detection in curvature scale space [J]. Pattern Recognition Letters, 2007, 28:545-554.
[120] DRIVE: Digital Retinal Images for Vessel Extraction, Website, http://www.isi.uu.nl/Research/Databases/DRIVE/ Last Visit: November, 2009.
[121] Qingyuan Liang, David Wong. Increased risk of branch retinal vein occlusion inretinal vascular arcades with arteriovenous crossings in the first order artery[C]. COS (Canadian Ophthalmological Society) 2010 annual meeting. June 2010,Quebec City, Quebec,Canada.
[122]赵晓芳,林土胜.视网膜血管图像特征点自动提取和分类[J].计算机工程与应用,2011,48(8):14-17.
[123] Jain A. K., Hong L., Bolle R. On-line fingerprint verification [J]. IEEE Transactions on Pattern Analyze and Machine Intelligence, 1997, 19(4):302-313.
[124] Tico M., Kuosmanen P. Fingerprint matching using an orientation-based minutia descriptor [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(8):1009-1014.
[125] Jea T. Y., Govindaraju V. A minutia-based partial fingerprint recognition system [J]. Pattern Recognition, 2005, 38(10):1672-1684.
[126] Ranade A., Rosenefld A. Point Pattern matehing by Relaxation [J]. PatternReeognition, 1980, 12(5):269-275.
[127]罗希平,田捷.自动指纹识别中的图像增强和细节点匹配算法[J].软件学报,2002, 13(5):946-955.
[128] Maltoni D., Maio D., Jain A.K., et al. Handbook of Fingerprint Recognition [M]. NewYork: Springer Verlag, 2003.
[129] Tan X. J., Bhanu Bir. A Robust Two Step Approach for Fingerprint Identification [J]. Pattern Recognition Letter, 2003, 24(13):2127-2134.
[130] Wang W., Li J. W., Chen W. M. Fingerprint minutiae matching based on coordinate system bank and global optimum alignment [A]. Process of 18th International Conference on Pattern Recognition [C]. Hong Kong: IEEE, 2006:401-404.
[131]罗荣芳.基于指节折痕的生物特征提取与识别研究[D].华南理工大学博士学位论文,2007,4.
[132] Jain A. K., Ross A., Prabhakar S. An introduction to biometric recognition [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(l):4-19.
[133]时鹏,田捷,苏琪等.基于奇异点邻近结构的快速指纹识别[J].软件学报,2008,19(12):3134-3145.
[134]边肇祺,张学工.模式识别[M].第二版.北京:清华大学出版社,2000.
[2]周钢,陈瑛,程建新等.糖尿病性视网膜血管管径改变[J].中国实用眼科杂志, 2005,23(3):238.
[3]林土胜,徐锦堂,梁庆源.视网膜血管管径量化及对眼底血管病变的应用价值[J].暨南大学学报(自然科学与医学版), 1999,20(2):33-36.
[4] Tascini G., Passerni G., Puliti P., et al. Retina Vascular Network Recognition [A]. Proceedings of the International Society for Optical Engineering [C]. Newport Beach: Society of Photo-Optical Instrumentation Engineers, 1993:322-329.
[5]闵鹊秋.高血压病视网膜病变[J].实用医院临床杂志, 2004,1(1):11.
[6] Chatterjee S., Chattopadhya S., Hope-Ross M., et al. Hypertension and the eye: Changing perspectives [J]. Journal of Human Hypertension, 2002, 16(10):667-675.
[7] Wong T. Y., Mitchell P. The eye in hypertension [J]. The Lancet, 2007, 369(9559):425-435.
[8] Klonoff D. C., Schwartz D. M. An economic analysis of interventions for diabetes [J]. Diabetes Care, 2000, 23(3):390-404.
[9]王爽.视网膜微血管异常与心脑血管健康评估[J].眼科, 2007, 16(z1):43.
[10] Chaudhuri S., Chatterjee S., Katz N., et al. Detection of blood vessels in retinal images using two-dimensional matched filters [J]. IEEE Transactions on Medical Imaging, 1989, 8(3):263-269.
[11] Sun Y. Automated identification of vessel contours in coronary arteriogram by an adaptive tracking algorithm [J]. IEEE Transactions on Medical Imaging, 1989, 8(1):78-88.
[12] Tolias Y. A., Panas S. M. A fuzzy vessel tracking algorithm for retinal images based Oil fuzzy clustering [J]. IEEE Transactions on Medical Imaging, 1998, 17(2):263-273.
[13] Hoover A., Kouznetsova V., Goldbaum M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response [J]. IEEE Transactions on Medical Imaging, 2000, 19(3):203-210.
[14] Jiang X. Y., Mojon D. Adaptive local shareholding by verification-basedmulti-threshold probing with application to vessel detection in retinal images [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(1):131-137.
[15]林土胜,秦华标,赖声礼.基于拆支跟踪法提取特征的视网膜血管形态识别[J].华南理工大学学报(自然科学版), 2000,28(5):54-58.
[16]朱宏擎.基于灰度-梯度共生矩阵的视网膜血管分割方法[J].上海交通大学学报, 2004,38(9):1485-1488.
[17]张恒义,蒋黔麟,虞亚军等.基于视网膜血管模型的图像分割与血管提取[J].电子学报, 1999,27(6):65-67.
[18]许雷,郑筱祥,俞锋等.基于眼底视网膜血管网络模型的血管提取方法[J].浙江大学学报(工学版), 1999,33(4):386-392.
[19]仇恒志,钟鼎苏.一种视网膜血管的分割方法[J].江西医学院学报, 2009,49(1):129-133.
[20]汤敏,王惠南.彩色视网膜血管图像的自动分割算法[J].仪器仪表学报, 2007,28(7):1281-1284.
[21]姚畅,陈后金.一种新的视网膜血管网络自动分割方法[J].光电子.激光, 2009,20(2):274-278.
[22] Wong T. Y., Klein R. Retinal arteriolar narrowing and risk of diabetes mellitus in middle-aged persons [J]. JAMA, 2002, 287(19):2528-2533.
[23] Klein R.,Klein B. E., Moss S. E., et al. Retinal vascular abnormalities in persons with typeⅠdiabetes [J]. The Wisconsin Epidemiologic Study of Diabetic Retinopathy: XVIII. Ophthalmology, 2003, 110:2118-2125.
[24]郭倩茹.视网膜微血管直径测量及与糖尿病关系的研究现状[J].中国煤炭工业医学杂志,2008,11(12):1982-1983.
[25]林土胜,杜明辉,徐锦堂.视网膜血管高血压交叉压迫征的量化研究[J].生物医学工程杂志, 2001,18(3):397-399.
[26] Qingyuan Liang, David Wong, Alan Berger, et al. Annular Vein Narrowing: a Possible Risk Factor in Branch Retinal Vein Occlusion with Different Artery-vein Patterns of Arteriovenous Crossings[C]. ASRS (American Society of Retinal Specialists) 28th Annual Meeting. August 2010, Vancouver, British Columbia, Canada.
[27]曹文轩.视网膜血管测量计[J].中华眼科杂志,1964, 11(1):67.
[28] Donoso L. A., Magargal L. E., Sanborn G., et al. Microcomputer application in retinal research [J]. Ophthalmology, 1982, 89(1): 81-85.
[29] Carsten S. Extracting Curvilinear Structures: A Differential Geometric Approach [A]. Proceedings of the 4th European Conference on Computer Vision [C]. Cambridge: Springer, 1996: 630-641.
[30] Yoshinobu S., Takahiro A., Masayuki H., et al. A viewpoint determination system for stenosis diagnosis and quantification in coronary angiographic image acquisition [J]. IEEE Transactions on Medical Imaging, 1998, 17(1): 121-137.
[31] James L., Andrew H., David S., et al. Measurement of retinal vessel widths from fundus images based on 2-D modeling [J]. IEEE Transactions on Medical Imaging, 2004, 23(10): 1196-1204.
[32] Thomas K., Guido G., Gabor S., et al. Multiscale detection of curvilinear structures in 2-D and 3-D image data [A]. Proceedings of International Conference on Computer Vision [C]. Los Alamitos: IEEE CS, 1995: 864-869.
[33] Chanussot J., Lambert P. An application of mathematical morphology to road network extraction on SAR images [A]. Proceeding of the International Symposium on Mathematic Morphology [C], Amsterdam: 1998:399-406.
[34] Zhao X. F., Duan W. W., Lin T.H., et al. A method of retinal vessel width measurement [A]. Proceedings of 2nd International Conference on Computer and Automation Engineering [C]. Singapore: IEEE CS, 2010, 443-446.
[35]廖勇军.视网膜图像处理关键技术研究[D].重庆大学硕士学位论文,2008,10.
[36] Yannis A. T., Stavros M. P. A fuzzy vessel tracing algorithm for retinal images based on fuzzy clustering [J]. IEEE Transactions on Medical Imaging, 1998, 17(2): 263-273.
[37] Liu I. and Sun Y. Recursive tracking of vascular networks in angiograms based on the detection and deletion scheme [J]. IEEE Transactions on Medical Imaging, 1993, 12(2): 334-341.
[38] Kostas H., Serafim N. E., Nicos M.,et al. Model-based morphological segmentation and labeling of coronary angiograms [J]. IEEE Transactions on Medical Imaging, 1999, 18(10): 1003-1015.
[39]陆建荣,斯海臣,郁道银.冠状动脉血管直径测量方法的研究[J].中国生物医学工程学报, 2005,24(4):510-512.
[40]林土胜,秦华标,赖声礼.视网膜血管可逆量化的方法与实现[J].华南理工大学学报(自然科学版), 1999,27(7):27-31.
[41] Aylward S. R., Bullitt E. Initialization, noise, singularities, and scale in height ridge traversal for tubular object centerline extraction [J]. IEEE Transactions on MedicalImaging, 2002, 21(2):61-75.
[42] Al-Diri B., Hunter A., Steel D. An active contour model for segmenting and measuring retinal vessels [J]. IEEE Transactions on Medical Imaging, 2009, 28(9):1488-1496.
[43] Zhou L., Rzeszotarski M. S., Singerman L. J., et al. The detection and quantification of retinopathy using digital angiograms [J]. IEEE Transactions actions on Medical Imaging, 1994, 13(4): 619-626.
[44] Gang L., Chutatape O., Krishnan M. Detection and measurement of retinal vessels in fundus images using amplitude modified second-order Gaussian filter [J]. IEEE Transactions on Medical Imaging, 2002, 49(2): 168-172.
[45] Lowell J., Hunter A., Steel D., et al. Measurement of retinal vessel widths from fundus images based on 2-D modeling [J]. IEEE Transactions on Medical Imaging, 2004, 23(10): 1196-1204.
[46]姚畅,陈后金.一种基于先验知识的视网膜血管宽度测量方法[J].中国科技论文在线, 2009,4(1):64-68.
[47]姚畅,陈后金,李居朋.基于过渡区提取的视网膜血管分割方法[J].电子学报, 2008, 36(5): 974-978.
[48]贾冬焱,郝立巍等.自动测量造影图像中血管中心线和宽度的新方法[J].中国生物医学工程学报, 2007,26(2):214-219.
[49]刘国才,王耀南,全惠敏.基于多层Mumford-Shah向量模型的彩色视乳头图像杯盘重建、分割与度量[J].中国生物医学工程学报, 2007,26(5):700-707.
[50] Hoover A., Goldbaum M. Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels [J]. IEEE Transactions on Medical Imaging, 2003, 22(8):951-958.
[51] Foracchia M., Grisan E., Ruggeri A. Detection of optic disc in retinal images by means of a geometrical model of vessel structure [J]. IEEE Transactions on Medical Imaging, 2004, 23(10):1189-1195.
[52] Sinthanayothin C., Boyce J. F., Cook H. L., et al. Automated localization of the optic disc, fovea, and retinal blood vessels from digital color fundus images [J]. British Journal of Ophthalmol, 1999, 83(8): 902-910.
[53] Barrett S., Naess E., Molvik T. Employing the Hough Transform to locate the optic disk [J]. Biomedical Sciences Instrumentation, 2001, 37(2):81-86.
[54] LI H., Opas C. Automatic location of optic disk in retinal images [A]. Proceedings of the International Conference on Image Processing [C]. Thessalonik: IEEE CS,2001:837-840.
[55] Walter T., Klein J. C., Massin P., et al. A contribution of mage 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.
[56] Youssif A., Ghalwash A., Ghoneim A. Optic disc detection from normalized digital fundus images by means of a vessels’direction matched filter [J]. IEEE Transaction on Medical Imaging, 2008, 27(1):11-18.
[57] Mahfouz A. E., Fahmy A. S. Ultrafast localization of the optic disc using dimensionality reduction of the search space [A]. Proceedings of the 12th International Conference on Medical Image Computing and Computer Assisted Intervention [C]. London: IEEE, 2009: 985-992.
[58] Robin G. D., Paik D. S., Johnston P. C., et al. Measurements of the aorta and its branches with helical CT [J]. Radiology, 1999,206 (3):823-829.
[59] Parida L., Geiger D., Hummel R. Junctions: Detection, classification, and reconstruction [J]. IEEE Transactions Pattern Analysis and Machine Intelligence, 1998, 20(7): 687-698.
[60] Tsai C. L., Stewart C. V., Tanenbaum H. L., et al. Model-based method for improving the accuracy and repeatability of estimating vascular bifurcations and crossovers from retinal fundus images [J]. IEEE Transactions on information Technology in Biomedicine, 2004, 8(2):122-129.
[61] Perez M. E., Highes A. D., Stanton A. V., et al. Retinal vascular tree morphology: a semi-automatic quantification [J]. IEEE Transactions on Biomedical Engineering, 2002, 49(8):912-917.
[62] Bevilacqua V. S., CambóL., Cariello G., et al. A combined method to detect retinal fundus features [A]. Proceedings of the European Conference on Emergent Aspects in Clinical Data Analysis [C]. Pisa: 2005.
[63]林土胜.视网膜血管形态识别与血管管径量化的研究[D].华南理工大学博士论文,2000,1.
[64] Calvo D., Ortega M., Penedo M. G., et al. Automatic detection and characterisation of retinal vessel tree bifurcations and crossovers in eye fundus images [J]. Computer Methods and Programs in Biomedicine, (2010), article in press
[65] Mari?o C., Penedo M. G., Penas M., et al. Personal authentication using digital retinal images [J]. Pattern Analysis and Applications, 2006, 9(1):21-33.
[66] Rahman N. A., Mohamed A. S., Rasmy M. E. Retinal identification [A]. Proceedings of International Biomedical Engineering Conference [C]. Cairo: IEEE CS, 2008.
[67] Ortega M., Penedo M. G., Rouco J., et al. Retinal verification using a feature points-based biometric pattern [J]. Eurasip Journal on Advances in Signal Processing, 2009, 2009(2009).
[68] Tan X. J., Bhanu B. A robust two step approach for fingerprint identification [J]. Pattern Recognition Letter, 2003, 24(13):2127-2134.
[69]李海英.眼底血管的识别和对比研究[D].吉林大学硕士学位论文,2006,12.
[70] Latha L., Pabitha M., Thangasamy S. A novel method for person authentication using retinal images [A]. Proceedings of International Conference on Innovative Computing Technologies [C]. Karur-Tamilnadu: IEEE CS, 2010.
[71] http://www.xshospital.com/info/detail/1996.html
[72] Haar F. Automatic localization of the optic disc in digital colour imges of the human retinal [D]. Master's thesis, Netherlands: Utrecht University, 2005.
[73] Hoover A. and Goldbaum M. Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels [J]. IEEE Transactions Medical Imaging, 2003, 22 (8):951–958.
[74] Pratt W. K. Digital image processing [M]. 2nd Edition, Wiley.
[75]刘祝华.图像去噪方法的研究[D].江西师范大学硕士学位论文,2005,5.
[76]张莹,王耀南.基于Gabor滤波器包络的人脸识别算法[J].中国图象图形学报, 2008,13(12):2314-2320.
[77]曹江中,戴青云,何家峰等.基于纹理分布和Gabor滤波器的虹膜识别算法[J].计算机工程,2006,32(9):199-200.
[78] Daugman J. G. Complete discrete 2-D Gabor transforms by neural networks for image analysis and compression [J]. IEEE Transaction on Acoustics, Speech and Signal Processing, 1988, 36(7):1169-1179.
[79]刘尚平,陈骥.基于Gabor滤波与数学形态学的视网膜图像增强方法[J].光电子.激光,2010,21(2):318-322.
[80]索爱黎.形态学图像分析:原理与应用[M].王小鹏,译.北京:清华大学出版社,2008: 62-65.
[81]张立国,杨瑾,李晶等.基于小波包和数学形态学结合的图像特征提取方法[J].仪器仪表学报,2010,31(10):2285-2289.
[82] Naegel B. Using mathematical morphology for the anatomical labeling of vertebrae from 3D CT-scan images [J]. Computerized Medical Imaging and Graphics, 2007, 31(3): 141-156.
[83]王慧锋,战桂礼,罗晓明.基于数学形态学的边缘检测算法研究及应用[J].计算机工程与应用,2009, 31(2):223-226.
[84]王艳芬.视网膜血管灰度图像血管检测方法的研究[D].华南理工大学硕士学位论文,2006.6.
[85] Otsu N. A threshold selection method form gray-level histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66.
[86] Gonzalez R. C., Woods R.E., Eddins S.L. Digital Image Processing Using Matlab [M].阮秋琦.北京:电子工业出版社, 2005:348-349.
[87]刘轩,刘佳宾.基于对比度受限自适应直方图均衡的乳腺图像增强[J].计算机工程与应用,2008,44(10):173-175.
[88] Canny J. A computational approach to edge detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, PAMI-8(6): 679-698.
[89] Stanton A. V., Mullaney P. A method of quantifying retinal microvascular alterations associated with blood pressure and age [J]. Journal of Hypertension, 1995, 13:41-48.
[90]许燕,胡广书等.基于Hessian矩阵的冠状动脉中心线的跟踪算法[J].清华大学学报(自然科学版), 2007,47(6):889-892.
[91] Lakemond R., Fookes C., Sridharan S. Affine adaptation of local image features using the hessian matrix [J]. Advanced Video and Signal Based Surveillance, 2009:496-501.
[92]乔立山,王玉兰,曾锦光.实验数据处理中曲线拟合方法[J].成都理工大学学报, 2004,31(1):91-95.
[93] Gregory E., Fasshauer. Toward approximate moving least squares approximation with irregularly spaced centers [J]. Computer Methods in Applied Mechanics and Engineering, 2004, 193(12):1231-1243.
[94]张淮清,俞集辉.线路电磁场测量数据的移动最小二乘拟合处理[J].高电压技术,2010,36(3):661-665.
[95] Qingyuan Liang, David Wong. Vein compression and angle pattern of arteriovenous crossing in branch retinal vein occlusion[C]. COS (Canadian Ophthalmological Society) 2009 annual meeting. June 2009, Toronto, Ontario, Canada.
[96] Staal J. J., Abramoff M. D., Niemeijer M., et al. Ridge based vessel segmentation incolor images of the retina [J]. IEEE Transactions on Medical Imaging, 2004, 23(4):501-509.
[97]张恒义,虞亚军等.计算机眼底血管图像分析诊断系统[J].生物医学工程学杂志, 1999,16(2):198-202.
[98] Qingyuan Liang, David Wong. The Roles of Artery-vein Relation of an Arteriovenous Crossing and Vein Bifurcation in Branch Retinal Vein Occlusion[C]. WOC (World Ophthalmology Congress) 2010, XXXII International Congress of Ophthalmology, 108th DOG Congress, June 2010, Berlin, Germany.
[99]黄叔仁,张晓峰.眼底病诊断与治疗[M].北京:人民卫生出版社,2003.2:230-237.
[100]刁颖敏.生物力学的原理与应用[M].上海:同济医科大学出版社,1991:160-167.
[101]郭萍,谢琪,刘礼恩.分支血管之间的夹角[J].中国现代医学杂志, 1999, 9(7): 35-36.
[102] Gagnon L., Lalonde M., Beaulieu M., et al. Procedure to detect anatomical structures in optical funds images [J]. IEEE Transactions on Medical Imaging, 2001:1218–1225.
[103] Li H., Chutatape O. A model-based approach for automated feature extraction in fundus images [A]. Proceedings of the 9th International Conference on Computer Vision [C], Beijing: IEEE, 2003: 394-399.
[104] Abramoff M. D., Niemeijer M., Suttorp-Schulten M. S. A., et al. Evaluation of a system for automatic detection of diabetic retinopathy from color fundus photographs in a large population of patients with diabetes [J]. Diabetes Care, 2008, 31(2):193–198.
[105]赵晓芳,林土胜,李碧.视网膜图像中视盘的快速自动定位方法[J].华南理工大学学报(自然科学版), 2011,39(2):71-75.
[106] Zhu X. L., Rangaraj M. Detection of the optic disc in images of the retina using the Hough transform [A]. Proceedings of the 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society [C]. Alberta: IEEE, 2008:3546-3549.
[107] Thanapong C., Sarat Y., Sun Z. H., et al. Edge detection of the optic disc in retinal images based on identification of a round shape [A]. Proceedings of the International Symposium on Communications and Information Technologies [C]. Laos: IEEE, 2008: 670-674.
[108] Thongnuch V., Uyyanonvara B. Automatic detection of optic disc from fundus images of ROP infant using 2D circular Hough transform [A]. Proceedings of the 2nd International Symposium on Biomedical Engineering [C]. Bangkok: IEEE, 2006: 328- 330.
[109]冯国进,顾国华,张保民.指纹图像预处理与特征提取[J].计算机应用研究,2004 (5):183-185.
[110] Wang L., Bhalerao A., Wilson R. Analysis of retinal vasculature using a multiresultion hermite model [J]. IEEE Transactions on Medical Imaging, 2007, 26(2):137-152.
[111] Soares J. V. B., Leandro J. J. G., Cesar R. M., et al. Retinal vessel segmentation using the 2-D gabor wavelet and supervised classification [J]. IEEE Transactions on Medical Imaging, 2006, 25(9):1214-1222.
[112] Lam B. S. Y. and Yan H. A Novel Vessel Segmentation Algorithm for Pathological Retina Images Based on the Divergence of Vector Fields [J]. IEEE Transactions on Medical Imaging, 2008, 27(2): 237-245.
[113] Sofka M., Stewart C. V. Retinal vessel centerline extraction using multiscale matched filters, confidence and edge measures [J]. IEEE Transactions on Medical Imaging, 2006, 25(12):1531-1546.
[114] Bhuiyan A., Nath B., Chua J., et al. Automatic detection of vascular bifurcations and crossovers from color retinal fundus images [A]. Proceedings of the 3rd International Conference on Signal-Image Technologies and Internet-Based Systems [C]. ShangHai: IEEE CS, 2007:711-718.
[115] Mokhtarian F., Suomela R. Robust image corner detection through curvature scale space [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(12):1376-1378.
[116]孙君顶,郭启强.张兆生基于曲率尺度空间的轮廓角点检测[J].光电工程,2009,36(7):78-82
[117] Han J. H., Poston T. T. Chord-to-point distance accumulation and planar curvature: A new approach to discrete curvature [J]. Pattern Recognition Letters, 2001, 22: 1133-1144.
[118] Awrangjeb M., Lu G. J. Robust image coner detection based on the chord-to-point distance accumulation technique [J]. IEEE Transactions on multimedia, 2008, 10(6):1059-1072.
[119] Zhang X., Lei M., Yang D., et al. Multi-scale curvature product for robust image corner detection in curvature scale space [J]. Pattern Recognition Letters, 2007, 28:545-554.
[120] DRIVE: Digital Retinal Images for Vessel Extraction, Website, http://www.isi.uu.nl/Research/Databases/DRIVE/ Last Visit: November, 2009.
[121] Qingyuan Liang, David Wong. Increased risk of branch retinal vein occlusion inretinal vascular arcades with arteriovenous crossings in the first order artery[C]. COS (Canadian Ophthalmological Society) 2010 annual meeting. June 2010,Quebec City, Quebec,Canada.
[122]赵晓芳,林土胜.视网膜血管图像特征点自动提取和分类[J].计算机工程与应用,2011,48(8):14-17.
[123] Jain A. K., Hong L., Bolle R. On-line fingerprint verification [J]. IEEE Transactions on Pattern Analyze and Machine Intelligence, 1997, 19(4):302-313.
[124] Tico M., Kuosmanen P. Fingerprint matching using an orientation-based minutia descriptor [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(8):1009-1014.
[125] Jea T. Y., Govindaraju V. A minutia-based partial fingerprint recognition system [J]. Pattern Recognition, 2005, 38(10):1672-1684.
[126] Ranade A., Rosenefld A. Point Pattern matehing by Relaxation [J]. PatternReeognition, 1980, 12(5):269-275.
[127]罗希平,田捷.自动指纹识别中的图像增强和细节点匹配算法[J].软件学报,2002, 13(5):946-955.
[128] Maltoni D., Maio D., Jain A.K., et al. Handbook of Fingerprint Recognition [M]. NewYork: Springer Verlag, 2003.
[129] Tan X. J., Bhanu Bir. A Robust Two Step Approach for Fingerprint Identification [J]. Pattern Recognition Letter, 2003, 24(13):2127-2134.
[130] Wang W., Li J. W., Chen W. M. Fingerprint minutiae matching based on coordinate system bank and global optimum alignment [A]. Process of 18th International Conference on Pattern Recognition [C]. Hong Kong: IEEE, 2006:401-404.
[131]罗荣芳.基于指节折痕的生物特征提取与识别研究[D].华南理工大学博士学位论文,2007,4.
[132] Jain A. K., Ross A., Prabhakar S. An introduction to biometric recognition [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(l):4-19.
[133]时鹏,田捷,苏琪等.基于奇异点邻近结构的快速指纹识别[J].软件学报,2008,19(12):3134-3145.
[134]边肇祺,张学工.模式识别[M].第二版.北京:清华大学出版社,2000.