NEW SAR IMAGE INTERPRETATION METHOD OF AIRCRAFT BASED ON JOINT TIME-FREQUENCY ANALYSIS

With the continuous improvement of Synthetic Aperture Radar(SAR) resolution, interpreting the small targets like aircraft in SAR images becomes possible and turn out to be a hot spot in SAR application research. However, due to the complexity of SAR imaging mechanism, interpreting targets in SAR images is a tough problem. This paper presents a new aircraft interpretation method based on the joint time-frequency analysis and multi-dimensional contrasting of basic structures. Moreover, SAR data acquisition experiment is designed for interpreting the aircraft. Analyzing the experiment data with our method, the result shows that the proposed method largely makes use of the SAR data information. The reasonable results can provide some auxiliary support for the SAR images manual interpretation.

Blind Detection of LSB Steganography in Grayscale Images

There are many detectors for the least significant bit(LSB)steganography which is broadly used in hiding information in the digital images.The length of the hidden information is one of the most important parameters in detecting steganographic information.Using 2-D gradient of a pixel and the distance between variables the proposed method gives the length of hidden information in natural grayscale images without original image.Extensive experimental results show good performance even at low embedding rate compared with other methods.Furthermore,the proposed method also works well disregarding the status of the embedded information.

Calibrating the linearity between grayscale and element content for X-ray KES imaging of alloys

Doped elements in alloys significantly impact their performance.Conventional methods usually sputter the surface material of the sample,or their performance is limited to the surface of alloys owing to their poor penetration ability.The X-ray K-edge subtraction(KES)method exhibits great potential for the nondestructive in situ detection of element contents in alloys.However,the signal of doped elements usually deteriorates because of the strong absorption of the principal component and scattering of crystal grains.This in turn prevents the extensive application of X-ray KES imaging to alloys.In this study,methods were developed to calibrate the linearity between the grayscale of the KES image and element content.The methods were aimed at the sensitive analysis of elements in alloys.Furthermore,experiments with phantoms and alloys demonstrated that,after elaborate calibration,X-ray KES imaging is capable of nondestructive and sensitive analysis of doped elements in alloys.

Research on Defect Detection of Wind Turbine Blades Based on Morphology and Improved Otsu Algorithm Using Infrared Images

To address the issues of low accuracy and high false positive rate in traditional Otsu algorithm for defect detection on infrared images of wind turbine blades(WTB),this paper proposes a technique that combines morphological image enhancement with an improved Otsu algorithm.First,mathematical morphology’s differential multi-scale white and black top-hat operations are applied to enhance the image.The algorithm employs entropy as the objective function to guide the iteration process of image enhancement,selecting appropriate structural element scales to execute differential multi-scale white and black top-hat transformations,effectively enhancing the detail features of defect regions and improving the contrast between defects and background.Afterwards,grayscale inversion is performed on the enhanced infrared defect image to better adapt to the improved Otsu algorithm.Finally,by introducing a parameter K to adjust the calculation of inter-class variance in the Otsu method,the weight of the target pixels is increased.Combined with the adaptive iterative threshold algorithm,the threshold selection process is further fine-tuned.Experimental results show that compared to traditional Otsu algorithms and other improvements,the proposed method has significant advantages in terms of defect detection accuracy and reducing false positive rates.The average defect detection rate approaches 1,and the average Hausdorff distance decreases to 0.825,indicating strong robustness and accuracy of the method.

Research on time-frequency cross mutual of motor imagination data based on multichannel EEG signal

At present,multi-channel electroencephalogram(EEG)signal acquisition equipment is used to collect motor imagery EEG data,and there is a problem with selecting multiple acquisition channels.Choosing too many channels will result in a large amount of calculation.Components irrelevant to the task will interfere with the required features,which is not conducive to the real-time processing of EEG data.Using too few channels will result in the loss of useful information and low robustness.A method of selecting data channels for motion imagination is proposed based on the time-frequency cross mutual information(TFCMI).This method determines the required data channels in a targeted manner,uses the common spatial pattern mode for feature extraction,and uses support vector ma-chine(SVM)for feature classification.An experiment is designed to collect motor imagery EEG da-ta with four experimenters and adds brain-computer interface(BCI)Competition IV public motor imagery experimental data to verify the method.The data demonstrates that compared with the meth-od of selecting too many or too few data channels,the time-frequency cross mutual information meth-od using motor imagery can improve the recognition accuracy and reduce the amount of calculation.

Blind Source Separation based on Time-Frequency Morphological Characteristics for Rigid Acoustic Scattering by Underwater Objects

Separation of the components of rigid acoustic scattering by underwater objects is essential in obtaining the structural characteristics of such objects. To overcome the problem of rigid structures appearing to have the same spectral structure in the time domain, time-frequency Blind Source Separation （BSS） can be used in combination with image morphology to separate the rigid scattering components of different objects. Based on a highlight model, the separation of the rigid scattering structure of objects with time-frequency distribution is deduced. Using a morphological filter, different characteristics in a Wigner-Ville Distribution （WVD） observed for single auto term and cross terms can be simplified to remove any cross-term interference. By selecting time and frequency points of the auto terms signal, the accuracy of BSS can be improved. A simulation experimental has been used to analyze the feasibility of the new method, with changing the pulse width of the transmitted signal, the relative amplitude and the time delay parameter. And simulation results show that the new method can not only separate rigid scattering components, but can also separate the components when elastic scattering and rigid scattering exist at the same time. Experimental results confirm that the new method can be used in separating the rigid scattering structure of underwater objects.

Grayscale Mapping of Historically Irrigated LandsUsing GIS

This document describes the use of grayscale mapping and GIS for identification of historical irrigated lands. Historical irrigated lands form the basis for water rights—a private property right in New Mexico that is bought and sold on the open market. Identification of irrigated land on historical photography is both a science and an art. Grayscale mapping of historic black and white photographs can aid in the identification of irrigated lands. GIS allows historical images to be geo-referenced and area computations to be performed on polygons that define the irrigated lands.

A Multi-Stream Scrambling and DNA Encoding Method Based Image Encryption

Information security has emerged as a key problem in encryption because of the rapid evolution of the internet and networks.Thus,the progress of image encryption techniques is becoming an increasingly serious issue and considerable problem.Small space of the key,encryption-based low confidentiality,low key sensitivity,and easily exploitable existing image encryption techniques integrating chaotic system and DNA computing are purposing the main problems to propose a new encryption technique in this study.In our proposed scheme,a three-dimensional Chen’s map and a one-dimensional Logistic map are employed to construct a double-layer image encryption scheme.In the confusion stage,different scrambling operations related to the original plain image pixels are designed using Chen’s map.A stream pixel scrambling operation related to the plain image is constructed.Then,a block scrambling-based image encryption-related stream pixel scrambled image is designed.In the diffusion stage,two rounds of pixel diffusion are generated related to the confusing image for intra-image diffusion.Chen’s map,logistic map,and DNA computing are employed to construct diffusion operations.A reverse complementary rule is applied to obtain a new form of DNA.A Chen’s map is used to produce a pseudorandom DNA sequence,and then another DNA form is constructed from a reverse pseudorandom DNA sequence.Finally,the XOR operation is performed multiple times to obtain the encrypted image.According to the simulation of experiments and security analysis,this approach extends the key space,has great sensitivity,and is able to withstand various typical attacks.An adequate encryption effect is achieved by the proposed algorithm,which can simultaneously decrease the correlation between adjacent pixels by making it near zero,also the information entropy is increased.The number of pixels changing rate(NPCR)and the unified average change intensity(UACI)both are very near to optimal values.

Fault Diagnosis for IC Engines Using Wavelet Packet and Image Processing

There are few applications of image processing technology for diagnosing andstate monitoring for internal combustion (IC) engines, which is discussed in detail in this paper.The time-frequency distribution images of cylinder head vibration signals are obtained bydecomposing them with a wavelet packet algorithm. It is the first time that we look attime-frequency distribution images from the point of images. Based on this, a new method forapplying image processing technology for diagnosing and state monitoring for internal combustionengines is presented in this paper. A valve fault diagnosis model is set up by image matching, whichis realized on a four-stroke, six-cylinder diesel engine. At the same time, some notes arepresented in this paper. It has been proved that it is of no good effect to diagnose with histogramsof time-frequency images generated by cylinder head vibration signals that have been processed witha wavelet packet algorithm. The reason is given in this paper. Comparisons of diagnosing effect arecarried out between noise-added signals and original signals. It has little effect on diagnosingresults after signals have been added with noise. The results show that this method has a clearphysical meaning and is of good engineering practicability, feasibility, good precision and highspeed.

CT反转与MRI在直肠癌直肠系膜筋膜中的应用比较研究

目的本研究主要目标为利用后处理工作站中的Invert-CT反转技术将常规CT扫描图像密度进行反转,可获得与MRI-T2WI相仿的图像,经过对比,评价经反转之后的多层螺旋CT(multidetector-row computed tomography,MDCT)图像在直肠系膜筋膜(mesorectal fascia,MRF)显示中的应用价值。材料与方法回顾分析因MRI扫描禁忌证,仅有术前CT检查的87例直肠腺癌患者影像,主观评价并比较常规CT图像和“常规CT+反转图像”对于腹膜反折及MRF显示情况、显示范围的差异,以术后病理结果为标准,比较常规CT图像和“常规CT+反转图像”对MRF侵犯的诊断准确率。回顾性收集同期直接行根治性手术治疗、术前MRI资料完整的123例直肠腺癌患者图像,主观评价MRI-T2WI图像中腹膜反折、MRF显示情况、显示范围,以术后病理结果为标准评价MRI诊断MRF侵犯的准确率。比较“常规CT+反转图像”与MRI-T2WI在腹膜反折、MRF显示情况、显示范围及MRF侵犯诊断准确性的差异。结果常规CT图像腹膜反折显示率为24.1%,“常规CT+反转图像”腹膜反折显示率为52.9%,“常规CT+反转图像”的腹膜反折显示率高于常规CT图像(P<0.001)。在MRF显示范围上,“常规CT+反转图像”的显示范围大于常规CT图像,在前、后、左、右四个位置上差异均有统计学意义(P均<0.001)。以病理学评价的环周切缘(circumferential resection margin,CRM)状态为金标准,常规CT图像诊断MRF侵犯的敏感度、特异度和准确率分别为73.3%、93.1%和81.6%;“常规CT+反转图像”诊断MRF侵犯的敏感度、特异度和准确率分别为100.0%、95.8%和96.6%。“常规CT+反转图像”诊断MRF侵犯的准确率高于CT常规图像(P=0.035)。矢状位MRI-T2WI图上腹膜反折显示率为80.5%,在腹膜反折显示方面MRI-T2WI优于反转CT(P<0.001)。在MRF显示范围上,“常规CT+反转图像”的显示范围与轴位MRI-T2WI图像相比,在后侧MRF显示范围方面有差异,MRI-T2WI能够显示的范围更大。以病理学评价的CRM状态为金标准,MRI图像诊断MRF侵犯的敏感度、特异度和准确率分别为100.0%、93.1%和93.5%。MRI图像和“常规CT+反转图像”诊断MRF侵犯的准确率差异无统计学意义(P=0.528)。结论常规CT图像经反转之后能够较好地显示并评价MRF状态,针对有MRI扫描禁忌证的患者,“常规CT+反转图像”可作为较好的替代影像学评价手段,为个体化诊断方案的制订提供重要的参考依据。

面向体育训练质量提升的教学视频图像规范动作分割方法

为了提升体育项目的训练质量,设计了教学视频图像规范动作分割方法.由于灰度图像只包含亮度信息,不包含颜色信息,因此对教学视频图像实施灰度转换,以提高图像的处理速度,降低后续的计算复杂度.基于空间梯度特征实施特征转换,采用梯度特征与高斯卷积操作相结合的方法,提取在时空域中的动作特征,通过统计动作序列的前后向帧间差分二维投影特征完成动作的快速检测.对多级时序卷积网络实施改进,通过增加阶段级联模块、双膨胀层以及分界生成模块来完善传统时序动作分割模型的性能.测试结果表明,设计方法的规范动作分割效果边缘清晰、细节完整,背景剔除的效果较好.随着动作复杂性的增长,设计方法的编辑分数与F1分数仅有少量下降,整体性能表现较为平稳且性能表现良好.

High-resolution grayscale image hidden in a laser beam

Images perceived by human eyes or recorded by cameras are usually optical patterns with spatially varying intensity or color profiles.In addition to the intensity and color,the information of an image can be encoded in a spatially varying distribution of phase or polarization state.Interestingly,such images might not be able to be directly viewed by human eyes or cameras because they may exhibit highly uniform intensity profiles.Here,we propose and experimentally demonstrate an approach to hide a high-resolution grayscale image in a square laser beam with a size of less than half a millimeter.An image with a pixel size of 300×300 nm is encoded into the spatially variant polarization states of the laser beam,which can be revealed after passing through a linear polarizer.This unique technology for hiding grayscale images and polarization manipulation provides new opportunities for various applications,including encryption,imaging,optical communications,quantum science and fundamental physics.

Grayscale image statistics of COVID-19 patient CT scans characterize lung condition with machine and deep learning

Background:Grayscale image attributes of computed tomography(CT)of pulmonary scans contain valuable information relating to patients with respiratory ailments.These attributes are used to evaluate the severity of lung conditions of patients confirmed to be with and without COVID-19.Method:Five hundred thirteen CT images relating to 57 patients(49 with COVID-19;8 free of COVID-19)were collected at Namazi Medical Centre(Shiraz,Iran)in 2020 and 2021.Five visual scores(VS:0,1,2,3,or 4)are clinically assigned to these images with the score increasing with the severity of COVID-19-related lung conditions.Eleven deep learning and machine learning techniques(DL/ML)are used to distinguish the VS class based on 12 grayscale image attributes.Results:The convolutional neural network achieves 96.49%VS accuracy(18 errors from 513 images)successfully distinguishing VS Classes 0 and 1,outperforming clinicians’visual inspections.An algorithmic score(AS),involving just five grayscale image attributes,is developed independently of clinicians’assessments(99.81%AS accuracy;1 error from 513 images).Conclusion:Grayscale CT image attributes can be successfully used to distinguish the severity of COVID-19 lung damage.The AS technique developed provides a suitable basis for an automated system using ML/DL methods and 12 image attributes.

基于红外热成像的煤矸识别方法研究

基于重介选煤、跳汰选煤、浮选、干法选煤、γ射线检测法的煤矸分选方法投资成本高、分选效率低、环境污染严重,基于CCD相机的煤矸分选方法准确率不高,基于X射线的煤矸分选技术会危害工作人员的健康。红外热成像技术不受光照、粉尘影响,且不会对人体造成伤害。提出了一种基于红外热成像的煤矸识别方法。首先,煤和矸石在传送带的输送下经过加热区域,红外热成像仪监测经均匀加热后的煤和矸石中心点的温度,得到煤和矸石加热后的温度并对经加热区域均匀加热后的煤和矸石进行拍摄,得到煤和矸石的红外灰度图像和红外彩色图像。然后,选用高斯滤波对煤和矸石的红外灰度图像、红外彩色图像进行预处理并提取特征,将红外灰度图像的灰度均值、最大频数对应的灰度值特征和红外彩色图像的G通道一阶矩、G通道二阶矩特征作为分选特征,将上述4个特征作为分类模型的输入。最后,采用支持向量机(SVM)进行分类识别,从而达到识别煤和矸石的目的。实验结果表明:基于红外热成像的煤矸识别方法对烟煤、无烟煤、褐煤的分选准确率均达到了98%以上,有良好的分类效果。

基于三维激光扫描技术的竣工盾构隧道渗漏水检测

渗漏水是隧道常见的病害,长期渗漏会导致隧道结构开裂、裂缝、钢筋腐蚀,威胁到隧道运营安全,因此对其检测一直受到重视。本文利用三维激光扫描技术实现了竣工盾构隧道渗漏水的位置及面积的自动检测。首先采用架站式三维激光扫描仪采集竣工隧道点云,基于修正后的反射强度值生成隧道衬砌表面灰度图,再采用膨胀法与腐蚀法对灰度图像进行预处理;然后利用连通域算法计算渗漏水位置及其面积;最后结合实际工程验证本文方法的实用性及准确性。结果表明,应用本文方法竣工隧道的渗漏水检测准确率达92%。

基于改进引导滤波算法的蜗轮齿廓边缘保持方法

在使用机器视觉方法测量蜗轮齿距过程中,工业相机采集的蜗轮齿廓图像极易受到高斯噪声和光照不均引起的轮廓伪影的影响。针对以上问题,提出了一种基于改进引导滤波算法的蜗轮齿廓边缘保持方法。首先,对原始蜗轮齿廓图像进行了滤波处理和二值化处理,滤波处理采用了改进的引导滤波算法,使用高斯函数构造权重系数替代了引导滤波算法中的均值权重系数,二值化处理使用最大类间方差进行了阈值分割;然后,对滤波后的图像与二值化图像进行了图像融合,对融合后的图像进行了拉普拉斯锐化处理;最后,进行了灰度拉伸对数变换,得到了增强后的图像,并采用实验验证了基于改进引导滤波算法的蜗轮齿廓边缘保持方法。研究结果表明:基于改进的引导滤波的蜗轮齿廓边缘保持算法在处理蜗轮齿廓边缘时,相比传统保边滤波算法,峰值信噪比可提高7.81%,图像对比度可提高43.6%,有效地增加了图像的信噪比和对比度;使用该蜗轮齿廓边缘保持算法增强后的蜗轮齿廓图像,当采用机器视觉测量其蜗轮齿距偏差时,左、右齿面单个齿距偏差为4.6μm和4.5μm,左、右齿面齿距累积偏差为16.5μm和16.6μm,测量结果均在允许的齿距偏差范围内。这说明采用蜗轮齿廓边缘保持算法增强后的蜗轮齿廓图像,去噪效果更好,蜗轮齿廓细节更清晰准确,有利于后续蜗轮齿廓特征的提取与齿距的测量。

基于模糊神经网络的舰船雷达图像弱小目标检测

舰船雷达图像信息的维度较高,导致弱小目标的关键特征难以被精准提取,降低了弱小目标检测的可靠性,因此提出一种基于模糊神经网络的舰船雷达图像弱小目标检测方法。该方法对舰船雷达图像进行背景校正,利用图像灰度值加性模型从图像中提取弱小目标。最后将提取的弱小目标输入到模糊神经网络中,输出的结果即为舰船雷达图像弱小目标检测结果。通过实验证明,在不同高斯噪声环境中,该方法能够准确地检测出雷达图像中的弱小目标,并具有较快的检测速度。

电成像测井中基于GA-RF的火山岩岩性识别

针对利用常规测井资料难以准确识别复杂火山岩岩性的问题,提出了一种基于GA-RF(遗传算法-随机森林)的利用电成像测井进行火山岩岩性识别的方法。首先,采用灰度共生矩阵(GLCM)方法提取电成像测井图像的能量、对比度、相关性、同质性等4个图像纹理特征,采用Tamura算法提取图像的粗糙度、对比度、方向度等3个图像纹理特征,并建立图像纹理特征数据集;然后,对数据集进行特征融合、降维,并利用ADASYN过采样算法平衡样本集,降低样本集不均衡对算法的影响;最后,通过遗传算法优化随机森林算法的参数,构建基于GA-RF的火山岩岩性识别模型(以下简称GA-RF模型),并与随机森林、GBDT、LightGBM等三种模型进行比较。实例分析结果表明,GA-RF模型岩性识别准确率可达94%左右,准确率高于3种对比算法。该方法有效地提高了火山岩岩性识别的精度和速度,可为样本不平衡问题以及测井方法识别岩性提供借鉴。

灰度变换下多模态刚性医学图像分层增强仿真

为了提升医学图像增强效果,有效保留图像细节,提出基于灰度变换的多模态刚性医学图像增强算法。对多模态刚性医学图像去噪处理,采用免疫优化算法对自适应阈值优化处理,选择最佳阈值。根据去噪结果通过小波变换将医学图像分解为多个不同区间,分别对各个区间实行灰度变换处理,根据变换后的结果获取分层增强效果,实现多模态刚性医学图像的整体增强。经实验测试结果表明,所提算法可以获取更加满意的医学图像增强效果,提高了图像清晰度,图像视觉效果显著增强。

基于CBAM和原型网络的小样本恶意软件分类模型

为解决小样本条件下恶意软件分类准确率低的问题,提出一种基于CBAM(convolutional block attention module)和原型网络的恶意软件分类模型。利用图像转换算法将恶意软件可执行文件转换为灰度图像;将残差连接和CBAM引入模型的特征嵌入模块,从通道和空间两个维度上增强关键特征表达,使得到的特征更具分辨性;提出联合损失函数,在距离交叉熵损失的基础上加入原型损失,通过减小类内距离的方式进一步扩增类间距离,使模型在样本数量有限的情况下取得良好的分类效果。实验结果表明,在每类恶意软件仅有5个样本的情况下,模型的分类准确率仍可达到83.12%。