Construction of saliency map and hybrid set of features for efficient segmentation and classification of skin lesion

Skin cancer is being a most deadly type of cancers which have grown extensively worldwide from the last decade. For an accurate detection and classification of melanoma, several measures should be considered which include, contrast stretching, irregularity measurement, selection of most optimal features, and so forth. A poor contrast of lesion affects the segmentation accuracy and also increases classification error. To overcome this problem, an efficient model for accurate border detection and classification is presented. The proposed model improves the segmentation accuracy in its preprocessing phase, utilizing contrast enhancement of lesion area compared to the background. The enhanced 2D blue channel is selected for the construction of saliency map, at the end of which threshold function produces the binary image. In addition, particle swarm optimization (PSO) based segmentation is also utilized for accurate border detection and refinement. Few selected features including shape, texture, local, and global are also extracted which are later selected based on genetic algorithm with an advantage of identifying the fittest chromosome. Finally, optimized features are later fed into the support vector machine (SVM) for classification. Comprehensive experiments have been carried out on three datasets named as PH2, ISBI2016, and ISIC (i.e., ISIC MSK‐1, ISIC MSK‐2, and ISIC UDA). The improved accuracy of 97.9, 99.1, 98.4, and 93.8%, respectively obtained for each dataset. The SVM outperforms on the selected dataset in terms of sensitivity, precision rate, accuracy, and FNR. Furthermore, the selection method outperforms and successfully removed the redundant features.     

Microscopic skin laceration segmentation and classification: A framework of statistical normal distribution and optimal feature selection

Among precision medical techniques, medical image processing is rapidly growing as a successful tool for cancer detection. Skin cancer is one of the crucial cancer types. It is identified through computer vision (CV) techniques using dermoscopic images. The early diagnosis skin cancer from dermoscopic images can be decrease the mortality rate. We propose an automated system for skin lesion detection and classification based on statistical normal distribution and optimal feature selection. Local contrast is controlled using a brighter channel enhancement technique, and segmentation is performed through a statistical normal distribution approach. The multiplication law of probability is implemented for the fusion of segmented images. In the feature extraction phase, optimized histogram, optimized color, and gray level co‐occurrences matrices features are extracted and covariance‐based fusion is performed. Subsequently, optimal features are selected through a binary grasshopper optimization algorithm. The selected optimal features are finally fed to a classifier and evaluated on the ISBI 2016 and ISBI 2017 data sets. Classification accuracy is computed using different Support Vector Machine (SVM) kernel functions, and the best accuracy is obtained for the cubic function. The average accuracies of the proposed segmentation on the PH2 and ISBI 2016 data sets are 93.79 and 96.04%, respectively, for an image size 512 × 512. The accuracies of the proposed classification on the ISBI 2016 and ISBI 2017 data sets are 93.80 and 93.70%, respectively. The proposed system outperforms existing methods on selected data sets.     

基于改进多尺度分形特征的红外图像弱小目标检测

为提高红外图像弱小目标检测的准确率和实时性,在分析用于红外图像增强的分形参数K相关的多尺度分形特征(MFFK)基础上,提出了一种基于改进多尺度分形特征(IMFFK)的红外图像弱小目标检测算法。首先,将基于地毯覆盖法的分形维数计算公式代入MFFK计算公式,提出了一种改进多尺度分形特征(IMFFK)用于图像增强。其次,对IMFFK特征计算进行简化,采用自适应阈值分割得到感兴趣目标区域,提出了一种具有较高计算效率的红外图像弱小目标检测算法。最后,通过仿真图像分析了主要参数对图像增强和算法耗时的影响,采用红外真实图像进行了算法检测性能测试,并与当前基于局部对比度测度的目标检测算法进行了对比。实验结果表明,提出的算法虽然在一些检测场景具有较多虚警,但能同时适用于弱小目标和较大目标检测,且无论目标为亮目标或暗目标。提出算法对于低分辨率红外图像(320×240)检测接近30 frame/s。提出算法具有较强的适用性,能够检测出红外图像中具有较高局部对比度的目标。     

基于改进特征金字塔的小目标增强检测算法

小尺寸的物体由于其在图像中分辨率相对较低的原因,在检测任务中容易被丢失和误判。针对目前目标检测算法对小尺寸目标检测精确度远低于其他尺寸目标检测精度的问题加以改进,将小尺寸目标特征增强融入特征金字塔结构。利用多尺度特征融合的特征增强能力丰富小尺寸目标特征层的特征信息,从而使小尺寸目标检测精准度得到提升。将改进特征金字塔结构应用于YOLOv3网络,实验对比研究表明,小尺寸目标检测精准度可以达到0.179,较原网络提升了22.6%。     

基于边缘检测小波变换的红外与可见光图像融合方法

简要地论述了图像融合中主要的三种像素级融合算法,即简单方法、基于塔形分解以及基于小波分解的融合方法,在现有的红外与可见光图像融合方法之上,提出了以边缘检测为基础的一种小波变换图像融合方法,并对融合效果进行了评价。实验结果表明,经该方法对红外与可见光图像的融合可以提供更多、更有效的信息,提高了图像的分辨效果和人眼对场景目标的发现和识别概率,融合效果较为理想。     

Microscopic brain tumor detection and classification using 3D CNN and feature selection architecture

Brain tumor is one of the most dreadful natures of cancer and caused a huge number of deaths among kids and adults from the past few years. According to WHO standard, the 700,000 humans are being with a brain tumor and around 86,000 are diagnosed since 2019. While the total number of deaths due to brain tumors is 16,830 since 2019 and the average survival rate is 35%. Therefore, automated techniques are needed to grade brain tumors precisely from MRI scans. In this work, a new deep learning‐based method is proposed for microscopic brain tumor detection and tumor type classification. A 3D convolutional neural network (CNN) architecture is designed at the first step to extract brain tumor and extracted tumors are passed to a pretrained CNN model for feature extraction. The extracted features are transferred to the correlation‐based selection method and as the output, the best features are selected. These selected features are validated through feed‐forward neural network for final classification. Three BraTS datasets 2015, 2017, and 2018 are utilized for experiments, validation, and accomplished an accuracy of 98.32, 96.97, and 92.67%, respectively. A comparison with existing techniques shows the proposed design yields comparable accuracy.     

Hybrid feature extraction techniques for microscopic hepatic fibrosis classification

Chronic liver diseases' hallmark is the fibrosis that results in liver function failure in advanced stages. One of the serious parasitic diseases affecting the liver tissues is schistosomiasis. Immunologic reactions to Schistosoma eggs leads to accumulation of collagen in the hepatic parenchyma causing fibrosis. Thus, monitoring and reporting the staging of the histopathological information related to liver fibrosis are essential for accurate diagnosis and therapy of the chronic liver diseases. Automated assessment of the microscopic liver tissue images is an essential process. For accurate and timeless assessment, an automated image analysis and classification of different stages of fibrosis can be employed as an efficient procedure. In this work, granuloma stages, namely cellular, fibrocellular, and fibrotic granulomas along with normal liver samples were classified after features extraction. In this work, a new hybrid combination of statistical features with empirical mode decomposition (EMD) is proposed. These combined features are further classified using the back‐propagation neural network (BPNN). A comparative study of the used classifier with the support vector machine is also conducted. The comparative results established that the BPNN achieved superior accuracy of 98.3% compared to the linear SVM, quadratic SVM, and cubic SVM that provided 85%, 84%, and 80%; respectively. In conclusion, this work is of special value that provides promising results for early prediction of the liver fibrosis in schistosomiais and other fibrotic liver diseases in no time with expected better prognosis after treatment.     

Brain tumor detection and classification: A framework of marker‐based watershed algorithm and multilevel priority features selection

Brain tumor identification using magnetic resonance images (MRI) is an important research domain in the field of medical imaging. Use of computerized techniques helps the doctors for the diagnosis and treatment against brain cancer. In this article, an automated system is developed for tumor extraction and classification from MRI. It is based on marker‐based watershed segmentation and features selection. Five primary steps are involved in the proposed system including tumor contrast, tumor extraction, multimodel features extraction, features selection, and classification. A gamma contrast stretching approach is implemented to improve the contrast of a tumor. Then, segmentation is done using marker‐based watershed algorithm. Shape, texture, and point features are extracted in the next step and high ranked 70% features are only selected through chi‐square max conditional priority features approach. In the later step, selected features are fused using a serial‐based concatenation method before classifying using support vector machine. All the experiments are performed on three data sets including Harvard, BRATS 2013, and privately collected MR images data set. Simulation results clearly reveal that the proposed system outperforms existing methods with greater precision and accuracy.     

一种基于多维特征提取的知识化制造系统故障监测方法

为了减少对知识化制造系统生产故障的误诊和漏诊,本文首先提出了一种新的基于多维特征提取的故障监测方法,该方法先对采集的信号进行多维特征提取,再通过归纳学习建立设备的正常状态空间,并以此来判断设备的故障状态。然后,提出一种故障误判概率控制方法。通过多维特征提取和误判概率控制,可以很好地减少对故障的漏判和误判。仿真实验证实了该故障监测方法的有效性。     

一种改进的基于差分曲率和对比度场的细节增强算法

针对图像细节增强过程中梯度对噪声敏感的缺点,本文提出了一种改进的基于差分曲率和对比度场的细节增强算法.首先,该算法利用差分曲率代替梯度值决定系数的放大倍数,以差分曲率作为自变量的放大系数函数考虑了更多的邻域像素,从而克服了图像梯度对噪声敏感的缺点;然后,利用该放大系数非线性地放大对比度场,并构造能量泛函;最后,通过变分方法得到增强后的图像.标准测试图像和工业X射线图像的实验结果表明,本文提出的算法在有效增强图像对比度的同时,能够较好地抑制噪声.     

基于区域分割的指纹奇异性检测及中心点计算

提出了一种基于区域分割的指纹奇异性检测以及中心点计算算法。该算法在对指纹奇异性分析的基础上,采用Gabor滤波、方差分析、图形二值化等分析手段,将指纹图样按不同的指纹脊线方向进行区域分割,根据合成图样每个元素邻域的灰阶变化次数以及相应的灰阶信息来检测指纹的奇异区。最后通过计算各奇异区质心的方法,实现指纹奇异点的定位,并进一步讨论了通过指纹奇异点计算指纹中心点的方法。实验结果表明,本算法可以有效实现不同类型指纹奇异性的检测及中心点的准确定位,算法简单,具有较好的鲁棒性。     

多模态特征融合与多任务学习的特种视频分类

特种视频(本文特指暴力视频)的智能分类技术有助于实现网络信息内容安全的智能监控。针对现有特种视频多模态特征融合时未考虑语义一致性等问题,本文提出了一种基于音视频多模态特征融合与多任务学习的特种视频识别方法。首先,提取特种视频的表观信息和运动信息随时空变化的视觉语义特征及音频信息语义特征;然后,构建具有语义保持的共享特征子空间,以实现音视频多种模态特征的融合;最后,提出基于音视频特征的语义一致性度量和特种视频分类的多任务学习特种视频分类理论框架,设计了对应的损失函数,实现了端到端的特种视频智能识别。实验结果表明,本文提出的算法在Violent Flow和MediaEval VSD 2015两个数据集上平均精度分别为97.97%和39.76%,优于已有研究。结果证明了该算法的有效性,有助于提升特种视频监控的智能化水平。     

变速器新产品故障特征提取与分类方法

针对汽车变速箱原始故障特征向量维数过高导致的检测效率低、准确率低的问题,提出一种基于阶次分析理论的特征提取方法和基于遗传算法—反向传播神经网络的特征选择与分类方法。首先运用阶次分析理论提取变速器的阶次域特征,与时域特征共同组成特征向量集;然后将类内类间距离比与惩罚系数之和作为目标函数值,利用遗传搜索策略对特征向量集进行特征选择,得到特征子集;最后用反向传播神经网络算法进行故障分类,得到检测结果,并通过实验验证了所提出方法的有效性。     

基于 MCP / sCMOS 的单光子成像探测系统及算法研究

针对单光子计数成像技术探测目标信号微弱信噪比低、所得图像目标区域不清楚、背景噪声严重等问题。 本文利用 270±5 nm 的日盲紫外滤光片、图像增益 710 5 的微通道板像增强器(MCP)、荧光屏和最大分辨率为 1 504×1 504 的科学级互补金属 氧化物半导体(sCMOS)等器件,设计了日盲紫外单光子探测系统,并通过时序控制获取了单光子光斑图像。 为了突出图像中的目 标区域,本文利用改进的形态学高帽变换算法,对光斑目标区域进行增强处理;随后利用三角阈值法对图像进行二值化处理,同时 利用连通域对目标区域的坐标进行提取;最后运用区域极值算法在原图中的目标区域进行单光子计数。 对紫外光源进行了单次 曝光时间为 80~100 ns 的系列成像和数据处理实验,实验结果验证了所设计的单光子成像探测系统和光子计数算法的可行性。     

自适应性多模态特征融合的远小困难目标检测

为了解决由LiDAR点云稀疏性和语义信息不足造成的远小困难物体检测困难的问题,提出了一种多模态数据自适应性融合的3D目标检测网络,充分融合了体素的多邻域上下文信息和图片多层语义信息。首先,设计了一种更适用于检测任务的改进残差网络,提取图片多层语义特征的同时,在低分辨率特征图中有效保留了远小物体的结构细节信息。每个特征图进一步通过来自所有后续特征图的语义信息进行语义增强。其次,提取具有不同感受野大小的多邻域上下文信息,弥补远小物体点云信息不足的缺陷,加强体素特征的结构信息和语义信息,以提高体素特征对物体空间结构和语义信息的表征能力及特征鲁棒性。最后,提出了一种多模态特征自适应融合策略,通过可学习权重,根据不同模态特征对检测任务的贡献程度进行自适应性融合。此外,体素注意力根据融合特征进一步加强有效目标对象的特征表达。在KITTI数据集上的实验结果表明,本方法以明显的优势优于VoxelNet,即在中等难度和困难难度下AP分别提高8.78%和5.49%。同时,与许多主流的多模态方法相比,本方法在远小困难物体的检测性能上具有更高的检测性能,即在中等和困难难度级别上,AP的性能比MVX-Net AP均高出1%。     

Integral DOE and MANOVA techniques for classification feature selection: using solder joint defects as an example

This study presents a novel approach for feature selection using an integrated DOE and MANOVA technique to classify solder joint defects for print circuit boards (PCBs). The main selection procedure includes three stages. The first stage adopts a single feature variable selection algorithm to eliminate poorly discriminated feature variables. The second stage, Plackett-Burman (PB) resolution III design, is then constructed to select the remaining feature variables. The MANOVA technique is then used to calculate the Pillai statistic as the response to the PB design of experiment, and statistical analysis is then executed to obtain the optimal multiple feature variables for multiple groups. The discriminate function classifier is used to evaluate the classification results. The experimental analysis results show that the proposed analysis procedure can acquire an optimum subset of features for classification.     

基于稀疏组lasso的脑机接口通道和特征选择研究

脑电信号(EEG)特征提取和分类是脑机接口(BCI)系统的核心问题之一。由于BCI系统中EEG信号多通道采样和特征向量的高维性,有效的特征选择算法已经成为研究中不可分割的一部分。针对EEG特征选择问题采用一种新方法:基于封装式稀疏组lasso的EEG融合特征的同时通道和特征选择方法。实验中将该方法与现有的通道选择和特征选择方法进行比较,结果表明,该方法更适用于高维融合特征的最优特征子集选择问题,且该算法稳定、时间成本低。此外,在保证错误率相当或较低的情况下,该方法能够同时实现通道和特征选择。国际BCI竞赛IV的两类运动想象信号的测试错误率为15.28%。     

结合多尺度边缘增强及自适应谷底检测的浮选气泡图像分割

针对浮选气泡图像噪声大、边界弱、传统谷底检测算法对不同类型气泡分割不具普遍性等问题,提出了一种结合Contourlet多尺度边缘增强及自适应谷底边界检测的气泡分割方法。该方法通过对气泡图像进行Contourlet分解,得到多尺度多方向高频子带;通过对各方向子带的高频系数进行非线性增益处理,实现边缘增强和噪声抑制。对和声搜索算法的"调音"策略和参数设定方法进行了改进,对不同类型气泡图像自适应地获取谷底边界检测算法的最优参数,提取谷底并进行形态学的边缘完善处理。最后进行了分割实验,并与其它方法做了比较。结果表明,采用该方法对不同类型气泡进行分割时,平均检测效率(DER)和准确率(ACR)分别为91.2%和90.6%,较传统分割方法有较大提高。该方法无需手工调节参数,自适应能力强,精度高。     

基于字符特征约束的自适应车牌校正提取

针对复杂多变环境中难以快速、精确提取车牌的问题,提出了一种利用字符特征智能校正提取车牌的方法。首先通过Gamma校正和Canny算子结合的方法在灰度图中实现自适应阈值边缘检测,解决了分割阈值选取的难题;然后应用字符特征约束条件提取特征轮廓,根据特征轮廓分布规律提取车牌候选区,避免复杂运算的同时提高了定位准确性;最后对候选区进行线性畸变校正并利用行灰度跳变统计实现了车牌真实性验证和精确提取,为后续的识别工作提供了良好条件。对不同环境中随机采集的700幅高清图像进行测试,综合提取准确率为96%,提取车牌字符规整、无多余残留信息。实验结果显示,该方法对图像中车牌状态、背景环境、光照条件等限制极少,具有更广的适用范围和更强的鲁棒性。     

面向机柜表面缺陷检测的不均匀光照和低亮度图像增强方法

光照条件是大尺寸机柜表面缺陷检测的重要影响因素。当光照分布不均匀或光照强度不足时,采集得到的机柜表面图像质量低,造成缺陷检测误差。为此,提出一种融合卡通纹理分解和最优双曲正切曲线的图像增强方法。首先,采用导向滤波将机柜表面图像分解为卡通图和纹理图,利用高斯尺度空间理论建立光照模型,实现不均匀光照去除;其次,研究图像的双曲正切曲线性质,通过图像加权拉伸实现低亮度图像增强;最后,采用对比度、亮度和灰度方差乘积对图像增强效果进行评价,同时对增强前和增强后的图像进行缺陷检测,进行对比分析验证。实验结果表明,该方法能实现光照不均且低亮度的机柜表面图像增强,机柜表面缺陷检测的准确率显著提升,召回率提高了29%,F值提高了21%。