视网膜图像中的黄斑中心检测

目的 在眼底图像分析中,准确的黄斑中心定位对于糖尿病性视网膜病变的计算机辅助诊断系统具有重要的意义。然而,由于光照不均匀、计算量大及病变的干扰给黄斑中心定位带来了巨大的挑战。因此,为了实现更为准确且高效的黄斑中心检测,提出一种基于血管投影和数学形态学的黄斑中心检测方法。方法 首先,基于数学形态学,提出一种自动的血管检测方法。其次,利用视盘区域的血管分布实现视盘中心的自动定位。再次,根据视盘和黄斑的解剖学结构先验信息,提取感兴趣区域。最后,在感兴趣区域内,通过数学形态学和特征提取定位黄斑中心。结果 本文提出的方法在两个标准的糖尿病视网膜病变数据库DIARETDB0和DIARETDB1上分别取得了96.92%和96.63%的成功率,且总成功率达到96.35%。此外,平均的执行时间分别为8.236 s和8.912 s。结论 实验结果表明,本文方法能快速和准确地定位黄斑中心且其性能明显地优于现有的黄斑中心检测方法。     

基于YOLO算法的眼底图像视盘定位方法

视盘的各个参数是衡量眼底健康状况和病灶的重要指标,视盘的检测和定位对于观察视盘的形态尤为重要。在以往的视盘定位研究中,主要根据视盘的形状、亮度、眼底血管的走向等特征使用图像处理的方法对眼底图像中视盘进行定位。由于人为因素影响较大,特征提取时间较长,且视盘定位效率低,因此提出一种基于YOLO算法的眼底图像视盘定位方法。利用YOLO算法将眼底图像划分为N×N的格子,每个格子负责检测视盘中心点是否落入该格子中,通过多尺度的方式和残差层融合低级特征对视盘进行定位,得到不同大小的边界框,最后通过非极大抑制的方式筛选出得分最高的边界框。通过在3个公开的眼底图像数据集(DRIVE、DRISHTI-GS1和MESSIDOR)上,对所提出的视盘定位方法进行测试,定位准确率均为100%,实验同时定位出视盘的中心点坐标,与标准中心点的平均欧氏距离分别为22.36 px、2.52 px、21.42 px,验证了该方法的准确性和通用性。     

基于自适应多尺度模板匹配的视盘检测方法

针对视盘检测易受光照和弱对比度影响的问题,提出了一种全新的视盘检测方法用于有效地定位和分割视盘.首先,采用预处理技术校正不均匀的光照和提高弱的对比度.然后,利用交替序列滤波和区域极大值技术提取一系列的视盘关键点.再次,利用提出的自适应多尺度模板匹配方法,计算每一个视盘关键点的相关系数,并将最大相关系数值所对应的关键点视为视盘中心.最后,基于获得的视盘中心,提取包含该中心位置的感兴趣区域,并在此基础上,利用Canny边缘检测算子和霍夫变换技术,实现视盘边缘的有效估计.该算法在DRIVE、DIRATEDB0、DIRATEDB1和ROC四个公共数据库上进行了测试,实验结果表明,提出算法的性能明显地优于现有方法.     

结合局部熵和鲁棒主成分分析的眼底图像硬性渗出物检测方法

针对眼科医生诊断眼底图像工作耗时且易出错的问题，提出一种无监督的眼底图像硬性渗出物检测方法。首先，通过形态学的背景估计方法去除血管、暗病变区域和视盘；然后，以图像亮度通道为初始图像，利用硬性渗出物在眼底图像中的局部性和稀疏性，结合局部熵和鲁棒主成分分析方法分解得到低秩矩阵和稀疏矩阵；最后，归一化稀疏矩阵得到硬性渗出物区域。实验结果显示，在e-ophtha EX和DIARETDB1公开数据库上，所提方法在病灶水平上灵敏性为91.13%和特异性为90%，在图像水平上准确率为99.03%，平均运行时间0.5 s；与支持向量机（SVM）和K-means方法相比灵敏性高且耗时少。     

Fovea center detection based on the retina anatomy and mathematical morphology

In this work, we present a new fovea center detection method for color eye fundus images. This method is based on known anatomical constraints on the relative locations of retina structures, and mathematical morphology. The detection of this anatomical feature is a prerequisite for the computer aided diagnosis of several retinal diseases, such as Diabetic Macular Edema. The proposed method is adaptive to local illumination changes, and it is robust to local disturbances introduced by pathologies in digital color eye fundus images (e.g. exudates). Our experimental results using the DRIVE image database indicate that our method is able to detect the fovea center in 37 out of 37 images (i.e. with a success rate of 100%). Using the DIARETDB1 database, our method was able to detect the fovea center in 92.13% of all tested cases (i.e. in 82 out of 89 images). These results indicate that our approach potentially can achieve a better performance than comparable methods proposed in the literature.     

视觉显著性的眼底图像视盘检测

目的 青光眼是导致失明的主要疾病之一,视盘区域的形状、大小等参数是青光眼临床诊断的重要指标。然而眼底图像通常亮度低、对比度弱,且眼底结构复杂,各组织以及病灶干扰严重。为解决上述问题,实现视盘的精确检测,提出一种视觉显著性的眼底图像视盘检测方法。方法 首先,依据视盘区域显著的特点,采用一种基于视觉显著性的方法对视盘区域进行定位;其次,采用全卷积神经网络（fully convolutional neural network,FCN）预训练模型提取深度特征,同时计算视盘区域的平均灰度,进而提取颜色特征;最后,将深度特征、视盘区域的颜色特征和背景先验信息融合到单层元胞自动机（single-layer cellular automata,SCA）中迭代演化,实现眼底图像视盘区域的精确检测。结果 在视网膜图像公开数据集DRISHTI-GS、MESSIDOR和DRIONS-DB上对本文算法进行实验验证,平均相似度系数分别为0.965 8、0.961 6和0.971 1;杰卡德系数分别为0.934 1、0.922 4和0.937 6;召回率系数分别为0.964 8、0.958 9和0.967 4;准确度系数分别为0.996 6、0.995 3和0.996 8,在3个数据集上均可精确地检测视盘区域。实验结果表明,本文算法精确度高,鲁棒性强,运算速度快。结论 本文算法能够有效克服眼底图像亮度低、对比度弱及血管、病灶等组织干扰的影响,在多个视网膜图像公开数据集上进行验证均取得了较好的检测结果,具有较强的泛化性,可以实现视盘区域的精确检测。     

视盘与黄斑同时定位检测的FPGA方法研究

在眼底图像自动分析中,视盘与黄斑的定位是实现利用计算机辅助诊断或筛查糖尿病视网膜病变的先决条件。提出一种实现眼底图像中视盘与黄斑同时定位检测的新方法,使用YOLOv4-tiny算法定位检测,将该算法移植到现场可编程逻辑门阵列（field programmable gate array,FPGA）。与传统方法相比,该方法不仅可以快速准确地同时定位眼底图像中视盘和黄斑的位置,而且也是利用高层综合（high level synthesis,HLS）语言和时分复用技术实现38层中型神经网络的首次尝试。实验采用公认的COCO数据集和Kaggle-Diabetic Retinopathy Detection竞赛中的381幅眼底图像对算法进行训练,将训练后的算法移植到FPGA平台后视盘和黄斑定位的平均正确率（mean average precision,mAP）为96.11%,检测一张图片只需要150.445?ms,在相关领域具有良好的临床应用前景。     

Detection and Classification of Hemorrhages in Retinal Images

Damage of the blood vessels in retina due to diabetes is called diabetic retinopathy (DR). Hemorrhages is the first clinically visible symptoms of DR. This paper presents a new technique to extract and classify the hemorrhages in fundus images. The normal objects such as blood vessels, fovea and optic disc inside retinal images are masked to distinguish them from hemorrhages. For masking blood vessels, thresholding that separates blood vessels and background intensity followed by a new filter to extract the border of vessels based on orientations of vessels are used. For masking optic disc, the image is divided into sub-images then the brightest window with maximum variance in intensity is selected. Then the candidate dark regions are extracted based on adaptive thresholding and top-hat morphological techniques. Features are extracted from each candidate region based on ophthalmologist selection such as color and size and pattern recognition techniques such as texture and wavelet features. Three different types of Support Vector Machine (SVM), Linear SVM, Quadratic SVM and Cubic SVM classifier are applied to classify the candidate dark regions as either hemorrhages or healthy. The efficacy of the proposed method is demonstrated using the standard benchmark DIARETDB1 database and by comparing the results with methods in silico. The performance of the method is measured based on average sensitivity, specificity, F-score and accuracy. Experimental results show the Linear SVM classifier gives better results than Cubic SVM and Quadratic SVM with respect to sensitivity and accuracy and with respect to specificity Quadratic SVM gives better result as compared to other SVMs.     

Combining algorithms for automatic detection of optic disc and macula in fundus images

This paper proposes an efficient combination of algorithms for the automated localization of the optic disc and macula in retinal fundus images. There is in fact no reason to assume that a single algorithm would be optimal. An ensemble of algorithms based on different principles can be more accurate than any of its individual members if the individual algorithms are doing better than random guessing. We aim to obtain an improved optic disc and macula detector by combining the prediction of multiple algorithms, benefiting from their strength and compensating their weaknesses. The location with maximum number of detectors’ outputs is formally the hotspot and is used to find the optic disc or macula center. An assessment of the performance of integrated system and detectors working separately is also presented. Our proposed combination of detectors achieved overall highest performance in detecting optic disc and fovea closest to the manually center chosen by the retinal specialist.     

A novel optic disc detection scheme on retinal images

Robust and effective optic disc detection is a necessary processing component in automatic retinal screening systems. In this paper, optic disc localization is achieved by a novel illumination correction operation, and contour segmentation is completed by a supervised gradient vector flow snake (SGVF snake) model. Conventional GVF snake is not sufficient to segment contour due to vessel occlusion and fuzzy disc boundaries. In view of this reason, the SGVF snake is extended in each time of deformation iteration, so that the contour points can be classified and updated according to their corresponding feature information. The classification relies on the feature vector extraction and the statistical information generated from training images. This approach is evaluated by means of two publicly available databases, Digital Retinal Images for Vessel Extraction (DRIVE) database and Structured Analysis of the Retina (STARE) database, of color retinal images. The experimental results show that the overall performance is with 95% correct optic disc localization from the two databases and 91% disc boundaries are correctly segmented by the SGVF snake algorithm.     

基于显著性检测和改进局部高斯分布拟合模型的眼底图像视盘边界自动提取

正确的视盘(OD)定位和分割是糖尿病视网膜病变自动筛选系统中的两个主要步骤.鉴于此,提出一种基于显著性目标检测和改进局部高斯分布拟合(LGDF)模型的视神经盘分割方法.该方法主要包含两个阶段:第一阶段,将显著性检测技术应用到增强的视网膜图像中实现视盘的自动定位;第二阶段,通过增加椭圆约束信息来改进局部高斯分布拟合(LGDF)模型分割视盘边界.使用公开数据库Diaretdbq对所提出方法的性能进行测试,并与其他先进的方法进行对比,结果验证了所提出方法的优越性和有效性.     

多相主动轮廓模型的眼底图像杯盘分割

目的 视盘及视杯的检测对于分析眼底图像和视网膜视神经疾病计算机辅助诊断来说十分重要,利用医学眼底图像中视盘和视杯呈现椭圆形状这一特征,提出了椭圆约束下的多相主动轮廓模型,实现视盘视杯的同时精确分割。方法 该算法根据视盘视杯在灰度图像中具有不同的区域亮度,建立多相主动轮廓模型,然后将椭圆形约束内嵌于该模型中。通过对该模型的能量泛函进行求解,得到椭圆参数的演化方程。分割时首先设定两条椭圆形初始曲线,根据演化方程,驱动曲线分别向视盘和视杯方向进行移动。当轮廓线到达视盘、视杯边缘时,曲线停止演化。结果 在不同医学眼底图像中对算法进行验证,对算法抗噪性、不同初始曲线选取等进行了实验,并与多种算法进行了对比。实验结果表明,本文模型能够同时分割出视盘及视杯,与其他模型的分割结果相比,本文算法的分割结果更加准确。结论 本文算法可以精确分割医学眼底图像中的视盘和视杯,该算法不需要预处理,具有较强的鲁棒性和抗噪性。     

Effective optic disc detection method based on swarm intelligence techniques and novel pre-processing steps

Diabetic retinopathy affects the vision of a significant fraction of the population worldwide. Retinal fundus images are used to detect the condition before vision loss develops to enable medical interventions. Optic disc detection is an essential step for the automatic detection of the disease. Several techniques have been introduced in the literature to detect the optic disc with different performance characteristics such as speed, accuracy and consistency. For optic disc detection, a nature-inspired algorithm called swarm intelligence has been shown to have clear superiority in terms of speed and accuracy compared to traditional detection algorithms. We therefore further investigated and compared several swarm intelligence techniques. Our study focused on five popular swarm intelligence algorithms: artificial bee colony, particle swarm optimization, bat algorithm, cuckoo search and firefly algorithm. This work also featured a novel pre-processing scheme that enhances the detection accuracy of the swarm techniques by making the optic disc region the highest grayscale value in the image. The pre-processing involves multiple stages of background subtraction, median filtering and mean filtering and is named Background Subtraction-based Optic Disc Detection (BSODD). The best result was obtained by combining our pre-processing technique, firefly algorithm and the parameters used for the algorithm. The obtained accuracy was superior to the other tested algorithms and published results in the literature. The accuracy of the firefly algorithm was 100%, 100%, 98.82% and 95% when using the DRIVE, DiaRetDB1, DMED and STARE databases, respectively.     

基于奇异值分解结合Harris的快速匹配方法研究

针对室内环境下视觉图像匹配速度慢、精度低等问题,提出一种基于奇异值分解结合Harris的快速匹配新方法.随机采集两组相邻的视觉图像作为研究对象,利用奇异值分解(SVD)对视觉图像进行压缩与重构.利用Harris角点检测算法对重构后的视觉图像进行特征角点的检测,然后结合归一化互相关(NCC)算法对视觉图像的特征角点进行一次粗匹配,最后采用随机抽样一致性(RANSAC)方法对粗匹配结果进行校正,实现特征点对的精匹配.实验表明:与传统的归一化互相关模板匹配算法相比,该算法不仅将视觉图像在室内环境下的误匹配率降低至2.35％,而且图像匹配的速率提升了3倍.     

Automated segmentation of optic disc region on retinal fundus photographs: Comparison of contour modeling and pixel classification methods

The automatic determination of the optic disc area in retinal fundus images can be useful for calculation of the cup-to-disc (CD) ratio in the glaucoma screening. We compared three different methods that employed active contour model (ACM), fuzzy c-mean (FCM) clustering, and artificial neural network (ANN) for the segmentation of the optic disc regions. The results of these methods were evaluated using new databases that included the images captured by different camera systems. The average measures of overlap between the disc regions determined by an ophthalmologist and by using the ACM (0.88 and 0.87 for two test datasets) and ANN (0.88 and 0.89) methods were slightly higher than that by using FCM (0.86 and 0.86) method. These results on the unknown datasets were comparable with those of the resubstitution test; this indicates the generalizability of these methods. The differences in the vertical diameters, which are often used for CD ratio calculation, determined by the proposed methods and based on the ophthalmologist's outlines were even smaller than those in the case of the measure of overlap. The proposed methods can be useful for automatic determination of CD ratios.     

Retinal optic disc localization using convergence tracking of blood vessels

Optic disc localization is of great diagnostic value related to retinal diseases, such as glaucoma and diabetic retinopathy. However, the detection process is quite challenging because positions of optic discs vary from image to image, and moreover, pathological changes, like hard exudates or neovascularization, may alter optic disc appearance. In this paper, we propose a robust approach to accurately detect the optic disc region and locate the optic disc center in color retinal images. The proposed technique employs a kernelized least-squares classifier to decide the area that contains optic disc. Then connected-component labeling and lumination information are used together to find the convergence of blood vessels, which is thought to be optic disc center. The proposed method has been evaluated over two datasets: the Digital Retinal Images for Vessel Extraction (DRIVE), and the Non-fluorescein Images for Vessel Extraction (NIVE) datasets. Experimental results have shown that our method outperforms existing methods, achieving a competitive accuracy (97.52 %) and efficiency (1.1577s).     

Fast document image comparison in multilingual corpus without OCR

This paper proposes a method to compare document images in multilingual corpus, which is composed of character segmentation, feature extraction and similarity measure. In character segmentation, a top-down strategy is used. We apply projection and self-adaptive threshold to analyze the layout and then segment the text line by horizontal projection. Then, English, Chinese and Japanese are recognized by different methods based on the distribution and ratios of text line. Finally, character segmentation with different languages is done using different strategies. In feature extraction and similarity measure, four features are given for coarse measurement, and then a template is set up. Based on the templates, a fast template matching method based on coarse-to-fine strategy and bit memory is presented for precise matching. The experimental results demonstrate that our method can handle multilingual document images of different resolutions and font sizes with high precision and speed.     

Singular point detection by shape analysis of directional fields in fingerprints

This paper presents a new fingerprint singular point detection method that is type-distinguishable and applicable to various fingerprint images regardless of their resolutions. The proposed method detects singular points by analyzing the shapes of the local directional fields of a fingerprint image. Using the predefined rules, all types of singular points (upper core, lower core, and delta points) can be extracted accurately and delineated in terms of the type of singular points. In case of arch-type fingerprints there exists no singular point, but reference points for arch-type fingerprints are required to be detected for registration. Therefore, we propose a new reference point detection method for arch-type fingerprints as well. The result of the experiments on the two public databases (FVC2000 2a, FVC2002 2a) with different resolutions demonstrates that the proposed method has high accuracy in locating each types of singular points and detecting the reference points of arch-type fingerprints without regard to their image resolutions.     

Development of algorithms for feature matching in the method for reconstucting high-precision digital surface models

The method for reconstructing high-precision digital surface models baseed on stereo matching of point and contour features is presented. Methods for extracting points and contours in images, and their subsequent matching are considered. Additionally the specific items of the proposed method are underlined from the point of view of using these image features for solving the final problem of detection features of the surface relief. Special attention is paid to the transition from local stereo matching to the global one. The necessity of this transition for successful solving the problem of a qualitative relief model with a minimal number of outliers is shown. The advantages of the developed method are demonstrated by the example of reconstructing a surface relief based on two stereo pairs of aerial images of different resolutions.