改进的K-Means高通量dPCR荧光图像分类算法

目的 为实现高通量dPCR荧光图像阳性点高精确度分类,提出一种改进的K-means高通量dPCR荧光图像分类算法。方法 首先,将预处理后的荧光图像进行像素灰度值统计,依据图像亮度自适应选择波峰波谷作为聚类中心,通过马氏距离度量确定像素簇类;然后,将粗分类结果进行开、闭运算及删除小面积对象等形态学处理;最后,利用3次连通域统计方法完成细分类、位置标识和计数。结果 选取4种通道825幅荧光图像进行检验,平均精确率达到99.06%,召回率达到98.97%,分类效果良好。结论 文中提出的改进K-means分类算法可以实现对高通量dPCR荧光图像的高精度分类和计数,对其他荧光图像分类识别具有一定借鉴意义。     

一种高通量dPCR荧光图像自适应增强算法

目的 为了改善荧光图像背景光照不均匀和对比度低的问题,提出一种荧光图像自适应亮度校正和低对比度增强算法。方法 根据光照成像原理,利用引导滤波提取出荧光图像的光照分量,通过改进的二维Gamma函数动态校正背景光照,利用Top-hat变换分离出校正后的前景和背景,对前景进行自适应直方图均衡化,以实现荧光图像自适应增强的目的。结果 对比传统算法,文中算法处理后的图像背景光照均匀,对比度增强效果明显,其中标准差平均提高了9.4倍,平均梯度平均提高了1.2倍,信息熵平均提高了0.2倍。结论 文中算法可以改善高通量dPCR荧光图像背景光照不均匀性,提高图像对比度,突出图像中隐藏的细节,对其他荧光图像处理也具有参考价值。     

基于SVM的捆装圆棒材计数方法

目的研究利用相机拍摄的捆装棒材端面图像进行棒材的自动计数方法。方法利用Hough变换提取端面圆的半径对图像尺寸进行规格化处理,使每个圆形端面具有近似统一的尺寸;利用滑动窗口的方法对检测窗口的中心点是否为圆棒材的中心进行判别,并标记判别结果;判别过程采用了一种SVM分类器的方法;通过在标记图上进行连通区搜索,统计棒材中心点区域的个数实现棒材计数;在测试图像库上对方法的有效性进行了测试实验。结果实验结果显示,文中方法在测试库上的正确率达到94%,其性能较模板匹配方法有显著优势。结论该方法的正确率较常规方法有很大提升,并且具有较好的鲁棒性,可应用于捆装圆棒材的自动计数问题。     

基于Adaboost算法选取和组合SVM的行人检测算法

行人检测是计算机视觉中一个重要的研究方向,为了提高行人的识别精度,将支持向量机(Sup-port Vector Machine,SVM)和Adaboost算法结合起来,SVM是基于结构风险最小化准则的新型机器学习算法,适合小样本学习并且能够有效地抑制过拟合问题,Adaboost基于最小化训练错误率,一般使用易训练的分类器作为弱分类器.由于SVM比较难训练,因此将样本集划分形成多个训练集,然后利用正样本和不同的负样本组成不同训练集反复训练,最后通过Adaboost对训练集生成的SVM模型筛选出具有最小错误率的SVM分类器并且采用投票机制形成最终的强分类器.实验结果表明,在FPPW(false positive per window)为10-5时检测率能够达到30%,检测效果优于单个SVM算法训练出来的分类器模型,用行人测试库测试,该方法取得了较好的检测效果并且具有较强的鲁棒性.     

基于多超平面支持向量机的图像语义分类算法

由于图像的低层可视特征与高层语义内容之间存在巨大的语义鸿沟,而基于内容的图像分类和检索准确性极大依赖低层可视特征的描述,本文提出了一种基于多超平面支持向量机的图像语义分类方法.多超平面分类器从优化问题的复杂度和运行泛化能力两方面进行研究,是最优分离超平面分类器一种显而易见的扩展.实验结果表明,本文提出的方法在图像语义分类的准确性方面要优于诸如采用色彩特征和纹理特征的支持向量机分类器的其它方法.     

基于复合分类特征的红外图像人体实时检测

针对红外图像中人体区域的检测问题,提出了一种基于复合分类特征的人体实时检测方法.首先根据红外图像中人体区域的特点,使用自适应的两级方向投影获得人体候选区域的可能位置,然后融合方向梯度直方图特征,人体形状特征及亮度分布惯性特征以充分描述人体区域的特点,并且采用支持向量机算法对候选目标中存在的人体进行分类检测.实验结果表明,本文提出的方法充分利用了复合分类特征各自的优点,具有较好的实时性和鲁棒性.     

基于支持向量机的遥感影像分类研究

以焦作地区部分IKONOS遥感影像为数据源,采用支持向量机(Support Vector Machine,SVM)分类器,通过解算最优化问题,在高维特征空间中寻找最优分类超平面,从而解决复杂数据的分类及回归问题。结果表明,利用SVM进行遥感图像分类的精度高,有明显的技术优势和应用前景。     

基于遗传算法优化支持向量机的超声图像缺陷分类

超声图像缺陷在分类时由于存在样本数量少、样本类别多、不易区分等问题,分类的准确率较低。针对这些问题,提出了基于遗传算法优化支持向量机的超声图像缺陷分类方法。该方法首先通过图像处理提取超声图像缺陷的特征数据,然后训练支持向量机作为超声图像缺陷分类器,最后采用遗传算法优化参数求得最优的分类器。实验结果表明,提出的超声图像缺陷分类器在识别率方面优于其他方法的分类器,综合识别率达到了90%,可以有效地辅助工作人员对超声图像缺陷进行分类识别。     

基于SVM的ECT图像重建算法

电容层析成像（ECT）技术是基于电容敏感机理的过程层析成像技术。ECT的图像重建是一个典型的有限样本非线性映射问题。支持向量机（SVM）作为一种小样本处理方法,具有较强的泛化能力,被认为是目前针对小样本分类问题的最佳理论。提出了一种基于SVM的四层神经网络的图像重建算法,仿真结果表明,该算法用于三相流图像重建具有较强的空间分辨率和泛化能力。     

基于支持向量机的多元文本分类研究

根据文本分类的特点，在对最小二乘支持向量机方法进行详细分析的基础上，创建了基于最小二乘支持向量机的多元文本分类器．实验表明，采用该文本分类器能够在保持较高分类精度和召回率的基础上，提高训练效率，具有一定的可行性．     

一种基于差影法及SVM的在线纸病检测分类方法

目的 解决目前纸病分类算法存在的实时性差、难以适应生产线在线检测要求等问题。方法 提出一种基于差影法和支持向量机的在线纸病检测分类方法。首先使用差影法来判断纸张是否含有纸病;对含有纸病的纸张进行打标机打标,同时存储图像,提取纸病区域外接矩形的特征向量;最后使用支持向量机对纸病进行分类。结果 将该方法与已有的BP神经网络以及朴素贝叶斯方法进行对比可知,分类正确率高于目前已有的分类方法,对于4种纸病的分类正确率均在90%以上,而且实时性好,更加适合于在线检测。结论 该方法可以有效地对纸病进行分类,满足生产线实时检测分类的要求。     

SVM and KNN Based CNN Architectures for Plant Classification

Automatic plant classification through plant leaf is a classical problem in Computer Vision. Plants classification is challenging due to the introduction of new species with a similar pattern and look-a-like. Many efforts are made to automate plant classification using plant leaf, plant flower, bark, or stem. After much effort, it has been proven that leaf is the most reliable source for plant classification. But it is challenging to identify a plant with the help of leaf structure because plant leaf shows similarity in morphological variations, like sizes, textures, shapes, and venation. Therefore, it is required to normalize all plant leaves into the same size to get better performance. Convolutional Neural Networks (CNN) provides a fair amount of accuracy when leaves are classified using this approach. But the performance can be improved by classifying using the traditional approach after applying CNN. In this paper, two approaches, namely CNN + Support Vector Machine (SVM) and CNN + K-Nearest Neighbors (kNN) used on 3 datasets, namely LeafSnap dataset, Flavia Dataset, and MalayaKew Dataset. The datasets are augmented to take care all the possibilities. The assessments and correlations of the predetermined feature extractor models are given. CNN + kNN managed to reach maximum accuracy of 99.5%, 97.4%, and 80.04%, respectively, in the three datasets.     

Classification COVID-19 Based on Enhancement X-Ray Images and Low Complexity Model

COVID-19 has been considered one of the recent epidemics that occurred at the last of 2019 and the beginning of 2020 that world widespread. This spread of COVID-19 requires a fast technique for diagnosis to make the appropriate decision for the treatment. X-ray images are one of the most classifiable images that are used widely in diagnosing patients’ data depending on radiographs due to their structures and tissues that could be classified. Convolutional Neural Networks (CNN) is the most accurate classification technique used to diagnose COVID-19 because of the ability to use a different number of convolutional layers and its high classification accuracy. Classification using CNNs techniques requires a large number of images to learn and obtain satisfactory results. In this paper, we used SqueezNet with a modified output layer to classify X-ray images into three groups: COVID-19, normal, and pneumonia. In this study, we propose a deep learning method with enhance the features of X-ray images collected from Kaggle, Figshare to distinguish between COVID-19, Normal, and Pneumonia infection. In this regard, several techniques were used on the selected image samples which are Unsharp filter, Histogram equal, and Complement image to produce another view of the dataset. The Squeeze Net CNN model has been tested in two scenarios using the 13,437 X-ray images that include 4479 for each type (COVID-19, Normal and Pneumonia). In the first scenario, the model has been tested without any enhancement on the datasets. It achieved an accuracy of 91%. But, in the second scenario, the model was tested using the same previous images after being improved by several techniques and the performance was high at approximately 95%. The conclusion of this study is the used model gives higher accuracy results for enhanced images compared with the accuracy results for the original images. A comparison of the outcomes demonstrated the effectiveness of our DL method for classifying COVID-19 based on enhanced X-ray images.     

Classification of Electroencephalogram Signals Using LSTM and SVM Based on Fast Walsh-Hadamard Transform

Classification of electroencephalogram (EEG) signals for humans can be achieved via artificial intelligence (AI) techniques. Especially, the EEG signals associated with seizure epilepsy can be detected to distinguish between epileptic and non-epileptic regions. From this perspective, an automated AI technique with a digital processing method can be used to improve these signals. This paper proposes two classifiers: long short-term memory (LSTM) and support vector machine (SVM) for the classification of seizure and non-seizure EEG signals. These classifiers are applied to a public dataset, namely the University of Bonn, which consists of 2 classes –seizure and non-seizure. In addition, a fast Walsh-Hadamard Transform (FWHT) technique is implemented to analyze the EEG signals within the recurrence space of the brain. Thus, Hadamard coefficients of the EEG signals are obtained via the FWHT. Moreover, the FWHT is contributed to generate an efficient derivation of seizure EEG recordings from non-seizure EEG recordings. Also, a k-fold cross-validation technique is applied to validate the performance of the proposed classifiers. The LSTM classifier provides the best performance, with a testing accuracy of 99.00%. The training and testing loss rates for the LSTM are 0.0029 and 0.0602, respectively, while the weighted average precision, recall, and F1-score for the LSTM are 99.00%. The results of the SVM classifier in terms of accuracy, sensitivity, and specificity reached 91%, 93.52%, and 91.3%, respectively. The computational time consumed for the training of the LSTM and SVM is 2000 and 2500 s, respectively. The results show that the LSTM classifier provides better performance than SVM in the classification of EEG signals. Eventually, the proposed classifiers provide high classification accuracy compared to previously published classifiers.     

基于图像的血型卡灌装质量在线检测系统

目的测量灌装后血型卡的固液高度,同时检测所灌液体中是否存在气泡。方法将摄像机捕获的血型卡图像经旋转矫正、初步裁剪、定位分割后,得到6个独立的微柱管,利用Sobel水平边缘检测方法分别提取出固液混合相和液相的水平边缘位置,进而计算相应高度,同时提出基于SVM的气泡检测方法,提取气泡的HOG特征,选择RBF核函数来训练检测模型,并建立分类模型,通过交叉验证的方法获得模型最佳参数。结果与手工测量结果进行对比,固液混合相高度误差不超过±0.1 mm,液相高度测量误差不超过±0.2 mm,气泡检测正确率高于97%,在效率上可满足实时检测的需要,高度测量和气泡检测的时间总和小于1.5 s,满足实时性要求。结论所设计的检测系统可以有效解决血型卡灌装质量的在线检测问题。     

基于V-矩的图像分类算法

基于一类不仅含有连续函数,还含有间断函数的正交完备函数系——V-系统,提出相应的V-矩函数,并将之应用到图像分类中.V-系统中基函数的间断特性,使得V-矩函数在描述含有多个闭合边界的形状时有特别的优势,这种优势表现为对这类复杂形状的特征提取更加准确.因此用V-矩可以得到一种图像分类的有效算法.在几个通用数据库中的图像分类实验表明,本文算法较Zernike矩、不变矩和几何中心矩有更高的准确率,对噪声不敏感,特别在含有多个闭合边界的复杂形状分类问题中,本文方法优势更为显著.     

基于深度学习的图像分类算法框架研究

目的 提高图像分类精度是实现自动化生产的基础,提出一种更加准确的图像分类方法,使自动化包装和生产更加高效.方法 基于ResNeSt特征图组的思想,通过引入通道域和空间域注意力机制,并将自适应卷积核思想和Gem池化引入空间域注意力模块,从而使网络在空间域注意力机制中能够对不同图片使用不同的感受野使其关注更重要的部分,提出一种具有通道域和空间域注意力机制,且具有很好移植性的图像分类网络模型结构.结果 文中方法提高了图像分类准确度,在ImageNet数据集上,top-1准确度为81.39％.结论 文中提出的ResNeSkt算法框架优于目前的主流图像分类方法,同时网络整体结构具有很好的移植性,可以作为图像检测、语义分割等其他图像研究领域的主干网络.     

Reversible Data Hiding in Encrypted Images Based on Prediction and Adaptive Classification Scrambling

Reversible data hiding in encrypted images (RDH-EI) technology is widely used in cloud storage for image privacy protection. In order to improve the embedding capacity of the RDH-EI algorithm and the security of the encrypted images, we proposed a reversible data hiding algorithm for encrypted images based on prediction and adaptive classification scrambling. First, the prediction error image is obtained by a novel prediction method before encryption. Then, the image pixel values are divided into two categories by the threshold range, which is selected adaptively according to the image content. Multiple high-significant bits of pixels within the threshold range are used for embedding data and pixel values outside the threshold range remain unchanged. The optimal threshold selected adaptively ensures the maximum embedding capacity of the algorithm. Moreover, the security of encrypted images can be improved by the combination of XOR encryption and classification scrambling encryption since the embedded data is independent of the pixel position. Experiment results demonstrate that the proposed method has higher embedding capacity compared with the current state-ofthe-art methods for images with different texture complexity.