线算子引导Gabor小波的视网膜血管分割

视网膜血管自动分割能辅助诊断某些眼底疾病和系统性血管疾病。为了提高血管自动分割的效率,因此提出了一种线算子引导Gabor小波的视网膜血管分割方法。利用线算子检测血管方向的最优匹配角,将其作为Gabor小波变换的旋转角构建4个不同尺度的Gabor小波,并提取4维Gabor小波特征,加上两个线强度和预处理后的图像灰度,构建7维特征向量,采用SVM进行分类。与其他基于Gabor小波的方法相比,本方法只需计算最优匹配角所对应方向的Gabor小波特征,大大降低了多尺度Gabor小波特征提取的计算量,此外线算子特征与Gabor小波特征的良好互补性,有利于提高血管与背景的辨别度。在DRIVE眼底数据库上进行实验,其平均准确率、灵敏度及特异性分别为0. 936 1、0. 823 8及0. 955 4,获得了不错的分割性能。     

改进支持向量机的电子邮件分类

电子邮件分类有利于垃圾邮件的过滤,节省网络资源。为了提高邮件分类的精度,提出了改进支持向量机的电子邮件分类器模型。首先提取电子邮件的原始特征,并采用主成分分析法对特征进行选择,减少特征数量,提高邮件分类效率;然后采用支持向量机建立电子邮件分类器,并对传统支持向量机参数选择方法进行改进,改善邮件分类效果,最后采用邮件分类的标准数据库——UCI进行性能分析。结果表明,改进支持向量机解决了当前电子邮件分类模型的不足,获得了理想的电子邮件分类效果,分类结果可以帮助管理人员拦截垃圾邮件。     

Image tamper detection and classification using support vector machines

The use of robust watermarks for attack characterisation is an area of considerable potential which has been largely overlooked to date. The authors extend their earlier work on accurate attack characterisation using a double watermarking technique to include a larger library of attacks. It is shown that the complexity of the double watermarking technique can be reduced with only a very small performance penalty. A further reduction in the algorithm complexity can be achieved by removing the thresholding process from the watermark estimation procedure. Analysis of the nature and location of the characterisation errors for the above methods is also presented.     

基于强化特征提取的视网膜血管分割

视网膜血管的分割精确率对眼科疾病和糖尿病早期诊断有着重要影响。面对现有方法在微血管与病变区域分割性能差的问题,本文提出一种强化提取血管特征的分割模型。该模型在编码部位引入多尺度特征提取残差模块(multi-scale feature extraction residual module,MFE-residual) 和多级残差空洞卷积层,用来扩展感受野,学习多层次图像特征,提高模型对血管信息的利用率;下采样和短连接部位分别融入轻量化注意力机制和多通道注意力模块,增加模型对血管的识别度,降低误分割的可能性。本文基于DRIVE和STARE两种公开数据集进行了实验,来验证改 进模型的分割能力。结果表明,两种数据上的准确率分别为0.965 2和0.971 5,灵敏度分别为0.820 5和0.825 6,与其他算法相比,分割性能更有优势。     

Supervised classification of marble textures using support vector machines

A novel approach is described for the supervised classification of marble textures in different classes according to visual appearance, using sum and difference histograms for texture analysis and feature extraction, and support vector machines for classification. Results show very good discrimination between classes.     

基于多尺度一致性与注意力机制的视网膜血管分割网络

针对现有的视网膜血管分割方法存在对微血管和毛细血管的分割能力不足,导致血管断连和末端血管漏分,造成视网膜血管分割性能不佳的问题,本文提出一种基于多尺度一致性与注意力机制的视网膜血管分割网络(multi-scale consistency and attention mechanism U-Net, MCAU-Net)。首先,该网络在瓶颈特征层嵌入注意力细化模块(attention refinement module, ARM),能有效细化瓶颈层冗余的特征,抑制背景等无关像素的权值。其次,将上下文特征融合模块(context fusion module, CFM)与传统的跳跃连接相结合,以此补充在特征提取过程中逐渐丢失的信息,加强网络对微血管和毛细血管的构建能力。最后,基于网络的多尺度输出设计了一种多尺度一致性的训练方式,以增强网络对不同尺度特征的敏感性。在DRIVE和CHASE＿DB1公开数据集上进行的对比实验表明本文网络具有良好的分割性能。     

应用支持向量机的纹理分类

提出了一种使用离散余弦变换(DCT)进行特征提取的应用支持向量机的纹理分类算法,并将文章中的算法与 KIM K I 等提出的不进行先期特征提取而直接将纹理图像送入支持向量机进行训练分类的算法进行比较。结果显示,文章中的算法可以取得更为准确的分类结果,能够大大降低分类错误率,并且分类结果受参数变化的影响很小。由此说明,在使用支持向量机进行纹理分类的过程中,准确的先期特征提取十分必要。     

Texture classification using logical operators

In this paper, a new algorithm for texture classification based on logical operators is presented. Operators constructed from logical building blocks are convolved with texture images. An optimal set of six operators are selected based on their texture discrimination ability. The responses are then converted to standard deviation matrices computed over a sliding window. Zonal sampling features are computed from these matrices. A feature selection process is applied and the new set of features are used for texture classification. Classification of several natural and synthetic texture images are presented demonstrating the excellent performance of the logical operator method. The computational superiority and classification accuracy of the algorithm is demonstrated by comparison with other popular methods. Experiments with different classifiers and feature normalization are also presented. The Euclidean distance classifier is found to perform best with this algorithm. The algorithm involves only convolutions and simple arithmetic in the various stages which allows faster implementations. The algorithm is applicable to different types of classification problems which is demonstrated by segmentation of remote sensing images, compressed and reconstructed images and industrial images.     

基于最小二乘支持向量机的飞机备件多元分类

飞机后续备件配置直接关系到装备的战备完好率和寿命周期费用,对备件的正确分类是进行备件配置决策的前提。支持向量机是采用结构风险最小化原则代替传统统计学中的基于大样本的经验风险最小化原则的新型机器学习方法,具有出色的学习分类能力和推广能力。研究了新型支持向量机算法-最小二乘支持向量机,设计了基于多元分类的最小二乘支持向量机,在此基础上,建立了飞机备件多元分类模型,并对某机型的备件进行了分类。结果表明,基于最小二乘支持向量机的飞机备件多元分类方法是有效、可行的。     

MS-UNet++:基于改进UNet++的视网膜血管分割

本文针对视网膜图像中细微血管特征提取困难导致其分割难度高等问题,提出了一种 基于端到端的神经网络嵌套视网膜血管分割模型算法(简称MS-UNet++),该算法选取了深度监督网络UNet++作为分割网络模型,提升特征的使用效率;引入MulitRes模块,改善低对比度环境下细小血管的特征学习效果,并在特征提取后加上SENet模块进行挤压和激励操作,从而增强特征提取阶段的感受野,提高目标相关特征通道的权重。基于DRIVE图像数据集的实验结果表明,该算法分割结果与真实结果之间的重叠率DICE值为83.64%,并交比IOU为94.83%,准确度ACC为96.79%,灵敏度SE为81.78%,较现有模型有一定的提升,可用于视网膜图像血管分割,为临床诊断提供辅助信息。     

Adaptive image enhancement for retinal blood vessel segmentation

Retinal blood vessel images are enhanced by removing the nonstationary background, which is adaptively estimated based on local neighbourhood information. The result is a much better segmentation of the blood vessels with a simple algorithm and without the need to obtain a priori illumination knowledge of the imaging system     

基于支持向量机的版面分割问题研究

版面分割是版面分析的重要组成部分,实现复杂版面的快速、有效分割是目前亟待解决的问题。针对复杂版面分割问题,文中将相位一致性统计特征和改进灰度共生矩阵的纹理特征相结合,得到一种新的组合特征向量。将该组合特征向量作为训练样本,最终得到基于支持向量机的复杂图像分割算法。实验结果表明,与其他方法相比,基于支持向量机的方法在版面分割任务中表现出了较好的召回率与准确率,能有效区分复杂图像中的各类不同区域,该方法为如何提高复杂版面的分割准确率提供了理论参考。     

Kernel-based adversarial attacks and defenses on support vector classification

While malicious samples are widely found in many application fields of machine learning, suitable countermeasures have been investigated in the field of adversarial machine learning. Due to the importance and popularity of Support Vector Machines (SVMs), we first describe the evasion attack against SVM classification and then propose a defense strategy in this paper. The evasion attack utilizes the classification surface of SVM to iteratively find the minimal perturbations that mislead the nonlinear classifier. Specially, we propose what is called a vulnerability function to measure the vulnerability of the SVM classifiers. Utilizing this vulnerability function, we put forward an effective defense strategy based on the kernel optimization of SVMs with Gaussian kernel against the evasion attack. Our defense method is verified to be very effective on the benchmark datasets, and the SVM classifier becomes more robust after using our kernel optimization scheme.     

基于双字典学习的眼底图像血管分割

为辅助诊断眼底疾病和部分心血管疾病,本文提 出一种基于双字典学习和多尺度线状结构检测的眼底图 像血管分割方法。首先在HSV颜色空间利用伽马矫正均衡眼底图像的亮度,并在Lab颜色空间 采用CLAHE 算法提升图像对比度,再采用多尺度线状结构检测算法突出血管结构得到增强后的特征图像 ;然后利用 K-SVD算法训练特征图像块和对应的手绘血管标签图像块,得到表示字典和分割字典,采用 表示字典得到 新输入特征图像块的重构稀疏系数,由该系数和分割字典获得血管图像块;最后进行图像块 拼接、噪声去 除和空洞填充等后处理得到最终分割结果。在DRIVE和HRF数据库测试,利用准确率、特异度 、敏感度 等八种评估指标来检验分割性能。其中,平均准确率分别达0.958和0.951,平均特异度分别 达到0.982 和0.967,平均敏感度分别达到0.709和0.762,表明该 方法具有较好的分割性能和通用性。     

支持向量机在目标分类中的应用

目标分类是一个决策过程,支持向量机是一种基于统计学习理论的机器学习方法,是目前较为理想的分类工具之一。本文介绍了支持向量机的理论背景和一些新的进展,及其在理论和实际应用中面临的难题。还对支持向量机在多元分类中的应用进行了讨论,并给出了实例。     

Multiclass support vector machines for EEG-signals classification.

In this paper, we proposed the multiclass support vector machine (SVM) with the error-correcting output codes for the multiclass electroencephalogram (EEG) signals classification problem. The probabilistic neural network (PNN) and multilayer perceptron neural network were also tested and benchmarked for their performance on the classification of the EEG signals. Decision making was performed in two stages: feature extraction by computing the wavelet coefficients and the Lyapunov exponents and classification using the classifiers trained on the extracted features. The purpose was to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. Our research demonstrated that the wavelet coefficients and the Lyapunov exponents are the features which well represent the EEG signals and the multiclass SVM and PNN trained on these features achieved high classification accuracies.     

支撑矢量预选取的双色Voronoi图方法

支撑矢量机是在统计学习理论的基础上发展出来的一种新的模式识别方法,在解决小样本、非线性及高维模式识别问题中表现出许多特有的优势,在支撑矢量机中,支撑矢量的选取相当困难,成为其应用的瓶颈问题。该文利用Voronoi图在特征空间特有的构造特性,提出了一种预先选取支撑矢量的新方法双色Voronoi图方法。该方法针对数据在空间的分布特性,在训练支撑矢量机以前,利用样本数据的双色Voronoi图确定候选的支撑矢量,然后在这些预选的矢量上进行学习。试验证明了该方法的有效性及可行性。     

Automatic segmentation of ultrasound images using morphological operators

A method for the automatic measurement of femur length in fetal ultrasound images is presented. Fetal femur length measurements are used to estimate gestational age by comparing the measurement to a typical growth chart. Using a real-time ultrasound system, sonographers currently indicate the femur endpoints on the ultrasound display station with a mouse-like device. The measurements are subjective, and have been proven to be inconsistent. The automatic approach described exploits prior knowledge of the general range of femoral size and shape by using morphological operators, which process images based on shape characteristics. Morphological operators are used first to remove the background (noise) from the image, next to refine the shape of the femur and remove spurious artifacts, and finally to produce a single pixel-wide skeleton of the femur. The skeleton endpoints are assumed to be the femur endpoints. The length of the femur is calculated as the distance between those endpoints. A comparison of the measurements obtained with the manual and with the automated techniques is included.     

Retinal fundus vasculature multilevel segmentation using whale optimization algorithm

The aim was to present a novel automated approach for extracting the vasculature of retinal fundus images. The proposed vasculature extraction method on retinal fundus images consists of two phases: preprocessing phase and segmentation phase. In the first phase, brightness enhancement is applied for the retinal fundus images. For the vessel segmentation phase, a hybrid model of multilevel thresholding along with whale optimization algorithm (WOA) is performed. WOA is used to improve the segmentation accuracy through finding the \(n{-}1\) optimal n-level threshold on the fundus image. To evaluate the accuracy, sensitivity, specificity, accuracy, receiver operating characteristic (ROC) curve analysis measurements are used. The proposed approach achieved an overall accuracy of 97.8%, sensitivity of 88.9%, and specificity of 98.7% for the identification of retinal blood vessels by using a dataset that was collected from Bostan diagnostic center in Fayoum city. The area under the ROC curve reached a value of 0.967. Automated identification of retinal blood vessels based on whale algorithm seems highly successful through a comprehensive optimization process of operational parameters.