Measurement method for human body anteflexion angle based on image processing

Measurement of the human body anteflexion angle is an essential method for evaluating human flexibility. In this study, a method based on edge detection is proposed for measuring the angle of human body anteflexion. In this technique, an adaptive Gaussian filter is used to filter an image while preserving as much of its edge information as possible. A 5 × 5 template is adopted to calculate the gradient amplitude and direction of the image. Moreover, the Otsu algorithm is used to compute the high and low thresholds of the gradient image, thereby rendering the algorithm adaptive and eliminating any need for manual threshold setting. After the edges are obtained, the feature points of the head, buttocks, and foot are extracted to calculate the anteflexion angle of the human body.     

基于生成对抗网络的文物图像修复与评价

目的 为了有效解决文物图像的不易保存和物理方法修复困难等问题,提出一种基于生成对抗网络的图像修复算法。方法 文中算法主要分为2个阶段,第1阶段通过Canny边缘检测器提取图像已知部分的边缘信息,利用1个生成器和1个鉴别器修复图像缺失边缘。第2阶段将第1阶段生成的边缘作为先验信息,通过1个生成器和2个鉴别器修复图像缺失部分。2个鉴别器由整体鉴别器和局部鉴别器组成,整体鉴别器用来评估修复后的图像整体连贯性,局部鉴别器用来查看待修复区域为中心的小区域局部一致性。结果 与传统算法对比,文中算法在提高生成图片纹理质量的基础上保证了全局语义结构一致性,在客观指标（峰值信噪比和结构相似性）上,较其他方法有更好的效果。结论 文中算法可以有效修复文物图像的缺损部分,尤其是结构复杂的大范围缺失,取得了良好的视觉效果,表明该算法有良好的修复性能。     

Semi-GSGCN: Social Robot Detection Research with Graph Neural Network

Malicious social robots are the disseminators of malicious information on social networks, which seriously affect information security and network environments. Efficient and reliable classification of social robots is crucial for detecting information manipulation in social networks. Supervised classification based on manual feature extraction has been widely used in social robot detection. However, these methods not only involve the privacy of users but also ignore hidden feature information, especially the graph feature, and the label utilization rate of semi-supervised algorithms is low. Aiming at the problems of shallow feature extraction and low label utilization rate in existing social network robot detection methods, in this paper a robot detection scheme based on weighted network topology is proposed, which introduces an improved network representation learning algorithm to extract the local structure features of the network, and combined with the graph convolution network (GCN) algorithm based on the graph filter, to obtain the global structure features of the network. An end-to-end semi-supervised combination model (Semi-GSGCN) is established to detect malicious social robots. Experiments on a social network dataset (cresci-rtbust-2019) show that the proposed method has high versatility and effectiveness in detecting social robots. In addition, this method has a stronger insight into robots in social networks than other methods.     

结合阈值去噪与边缘优化的图像增强算法

针对图像在传输过程中容易出现干扰的问题,该文通过研究图像的增强技术,通过对比分析,提出了一种结合阈值去噪与边缘优化的图像增强算法,该算法结合小波Contourlet 变换与人眼的视觉固有特性,有效地对分解后的图像系数进行分类,并结合改进边缘优化算法的增益因子来优化边缘区信号;而非边缘区采用改进后的软阈值去噪算法进行去噪处理.经实验,该算法具有准确性高与去噪能力强的特性,能够在去噪的同时有效保护边缘信号,与预期目标相符,具有一定的实用价值.     

基于视觉的驾驶机器人导航技术

对驾驶机器人的视觉导航技术进行了研究,提出了一种快速可靠的车辆引导线检测算法.该算法首先对感兴趣的移动窗口进行有条件的边缘检测,进而引入了梯度方向直方图的处理思想,制定了车辆引导线边缘候选点集与有效点集的筛选算法,最后,通过所提出的一种基于标量化处理Kalman滤波方法实现了引导线特征参数的快速准确提取.试验表明,本文提出的检测算法能够满足复杂路况下的导航需要,具有30ms/帧的实时处理速度.     

基于图像处理技术的五金件表面缺陷检测研究

为实现图像处理技术在表面缺陷检测中的应用,取代传统人工检测的方式,设计开发了一套五金件表面缺陷检测系统,研究了镀镍五金件表面图像在线处理算法,包括边缘检测算法、位置修正算法、标定算法和检测算法,实现了五金件表面缺陷视觉检测.同时提出一种阈值反馈算法,用实际缺陷值反馈验证理论缺陷值,最终得到可靠的缺陷阈值,判断表面缺陷....     

基于改进多阈值小波包的去噪算法及应用

提出一种改进多阈值小波包的去噪算法,解决了单一阚值对噪声去除不完全和对一些有用信号无差别去除的问题。应用在智能交通的图像去噪中,解决了不完全及错误去除图像信息的问题。首先采用小波包分解重构算法对图像进行预处理,得到更多的边缘细节。然后针对不同能量对应不同频段的特点,自适应地合理设置阈值,对不同频段下的噪声采用不同阈值去除。实验表明,该方法有效去除噪声,保留了图像的边缘和细节。     

基于最近邻搜索耦合近邻损耗聚类的图像伪造检测算法

目的为了解决当前图像伪造检测算法在对图像进行伪造检测时,主要依靠全局搜索的方式来完成特征点匹配,导致其检测效率较低,且在对复杂伪造图像进行检测时,易出现检测精度不高和检测错误的不足。方法提出基于最近邻搜索耦合近邻损耗聚类的图像伪造检测算法。首先引入积分图像的方法,对图像进行预处理,借助Hessian矩阵行列式来提取特征点。利用特征点构建圆形区域,通过求取圆形区域内Haar小波响应获取特征点的特征描述符。然后通过特征描述符建立KD树索引,利用最近邻搜索方法代替SURF中全局搜索的方法,对SURF进行改进,完成特征点的匹配。最后,利用特征点间的近邻关系求取近邻函数值,通过近邻函数值对特征点进行聚类,完成图像的伪造检测。结果实验结果显示,与当前图像伪造检测算法相比,所提算法具有更高的检测效率以及更高的检测正确度。结论所提算法具备较高的检测精度,在印刷防伪与信息安全等领域具有较好的应用价值。     

Improved cuckoo search with particle swarm optimization for classification of compressed images

The need for a general purpose Content Based Image Retrieval (CBIR) system for huge image databases has attracted information-technology researchers and institutions for CBIR techniques development. These techniques include image feature extraction, segmentation, feature mapping, representation, semantics, indexing and storage, image similarity-distance measurement and retrieval making CBIR system development a challenge. Since medical images are large in size running to megabits of data they are compressed to reduce their size for storage and transmission. This paper investigates medical image retrieval problem for compressed images. An improved image classification algorithm for CBIR is proposed. In the proposed method, RAW images are compressed using Haar wavelet. Features are extracted using Gabor filter and Sobel edge detector. The extracted features are classified using Partial Recurrent Neural Network (PRNN). Since training parameters in Neural Network are NP hard, a hybrid Particle Swarm Optimization (PSO) – Cuckoo Search algorithm (CS) is proposed to optimize the learning rate of the neural network.     

A Model for Helmet-Wearing Detection of Non-Motor Drivers Based on YOLOv5s

Detecting non-motor drivers’ helmets has significant implications for traffic control. Currently, most helmet detection methods are susceptible to the complex background and need more accuracy and better robustness of small object detection, which are unsuitable for practical application scenarios. Therefore, this paper proposes a new helmet-wearing detection algorithm based on the You Only Look Once version 5 (YOLOv5). First, the Dilated convolution In Coordinate Attention (DICA) layer is added to the backbone network. DICA combines the coordinated attention mechanism with atrous convolution to replace the original convolution layer, which can increase the perceptual field of the network to get more contextual information. Also, it can reduce the network’s learning of unnecessary features in the background and get attention to small objects. Second, the Rebuild Bidirectional Feature Pyramid Network (Re-BiFPN) is used as a feature extraction network. Re-BiFPN uses cross-scale feature fusion to combine the semantic information features at the high level with the spatial information features at the bottom level, which facilitates the model to learn object features at different scales. Verified on the proposed “Helmet Wearing dataset for Non-motor Drivers (HWND),” the results show that the proposed model is superior to the current detection algorithms, with the mean average precision (mAP) of 94.3% under complex background.     

一种精确的医学细胞图像边缘检测法

细胞边缘检测是进行细胞形态分析的基础,其检测结果直接影响病情分析和诊断的结果。传统的边缘检测算子由于受噪声影响比较大,无法检测细胞可靠的边缘位置,因而不宜应用于细胞形态分析。提出一种用迭代算法求图像分割最佳阈值和运用数学形态学的腐蚀算法实现轮廓提取相结合的细胞图像边缘精确检测算法,并给出仿真实例。与传统的边缘检测算子Laplacian-Gauss算子、Sobel算子相比较,该算法具有检测精度高和抗干扰能力强的优点。     

A sub-pixel edge detection algorithm based on Zernike moments

Abstract

A novel hybrid technique of combining an improved morphological gradient operator and Zernike moments, named MGZ edge detection algorithm, is developed to meet the stringent requirements for measuring accuracies of charge coupled device metrology system. The mathematical morphological gradient and Zernike moment algorithm are discussed based on the pixels grey-scale and spatial structure information of the images. To improve the algorithm process, the image edge is oriented and extracted by using improved morphological gradient operator firstly; then, the calculation errors of the typical ideal step edge model are analysed and corrected by the proposed error compensation formula. The edge point is relocated with sub-pixel accuracy by means of Zernike moment operator based on the edge point vectors and the threshold value. Finally, the sub-pixel edge detecting of the image is attained. The extensive experimental results show that the measuring error of the edge point is compensated reliably and accurately, and the new algorithm has short operation time, more precise and stronger robustness to noise than the prior similar algorithms. Meanwhile, the proposed method can well meet the need of charge coupled device metrology system for sub-pixel edge detection.     

基于拉普拉斯金字塔分解的多尺度边缘检测

边缘表现为图像中具有奇异性点的集合,利用改进的拉普拉斯金字塔分解捕获这些奇异性点,得到各尺度下的带通图像,通过分析,得出分解后的带通图像在边缘处产生零交叉点,构造统计量帮助提取零交叉点,再通过多尺度边缘融合实现多尺度边缘提取.与LOG和Canny边缘检测的对比实验表明,所建立的算法能够可靠、有效、精确的获得图像的边缘.     

基于环形特征的卷积神经网络轮毂识别

针对实际生产中不同种类轮毂的混流生产问题,提出了一种基于环形特征的卷积神经网络轮毂识别算法。将直角坐标下的环形轮毂映射到极坐标中,归一化为标准形式的矩形,提取轮毂图像的环形特征信息,减少冗余特征产生的影响;设计了一种改进的VGG网络架构,利用深度可分离卷积打破输出通道维度与卷积核大小的联系,在不损失网络性能的同时降低了计算量,能够在实际生产中轮毂识别任务在有限的算力情况下实时进行计算;从有效性和实时性两个方面对轮毂识别算法进行评估,且通过Inception V3、SVM、KNN等模型的对比实验,验证了该算法可以实时地对轮毂自适应分类。实验表明: 该方法对轮毂图像的处理精度达到99%以上,单幅图像平均处理时间降低至11.78ms。     

基于改进MultiResUNet网络的甲状腺超声图像分割

甲状腺超声图像分割在临床超声图像研究中有很重要的意义。针对甲状腺超声图像信噪比低,斑点噪声多,且甲状腺形态不确定等问题,提出了一种改进的MultiResUNet分割网络(称为Oct-MRU-Net网络)。该方法在MultiResUNet网络的基本结构的基础上引入Octave卷积,并采用改进的Inception模块学习不同空间尺度的特征,将训练过程中的特征图按通道方向分为高低频特征。其中,高频特征描述图像细节和边缘信息,低频特征描述图像整体轮廓信息。在甲状腺超声图像分割过程中可以重点关注高频信息,减少空间冗余,从而实现对边缘更加精细的分割。实验结果表明,Oct-MRU-Net网络的性能相较于U-Net网络和MultiResUNet网络都有较大的提升,说明该网络对甲状腺超声图像的分割效果较好。     

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.     

改进的自适应阈值Canny边缘检测

针对传统Canny边缘检测算法的阈值需要人为设定的缺陷,本文提出了一种新的自适应改进方法.该方法-根据梯度直方图信息,提出梯度差分直方图的概念,同时,对图像进行自适应分类处理,使得算法不仅不需人工设定阈值参数,而且还能有效地避免Canny算法在边缘寻找中的断边和虚假边缘现象.对边缘信息丰富程度不同的灰度图和彩色图像运用该方法寻找边缘的实验结果表明,对于在目标与背景交界处的多数像素梯度幅值较大的图片,该算法具有边缘检测能力强、自适应能力强的优点.     

基于图像识别的铝塑包装材料边缘检测

目的为了提高铝塑类包装材料的边缘检测精度,基于图像识别技术设计一种边缘检测方法。方法介绍Canny边缘检测算法,针对其双阈值选择比较困难、边缘检测精度不高等问题,利用Ostu算法实现高、低阈值的选取。基于FPGA(现场可编程门阵列)和DSP(数字信号处理器)搭建一种图像检测系统,并给出系统框图及FPGA内部结构,即异步FIFO模块、串入并出模块、像素窗口刷新模块、数据处理模块以及配套电路等,并以药品铝塑泡罩包装为例进行实验研究。结果改进的Canny算法在保证处理速度的前提下,所检测图像清晰细致,能够得到完整边缘。结论该方法具有准确度高、稳定可靠、识别速度快等特点,可满足包装过程产品检测要求。     

基于改进YOLOv4的焊接件表面缺陷检测算法

目的 针对真实复杂的工业场景下焊接件表面缺陷检测精度低、速度慢和图像噪声大等问题,提出一种基于卷积神经网络的改进YOLOv4焊接件表面缺陷检测算法。方法 该模型基于YOLOv4算法,首先,考虑到存储和计算资源的限制,使用了轻量级网络GhostNet替换YOLOv4的主干特征提取网络(Backbone)CSPDarknet53;其次,在GhostNet网络结构中嵌入改进的通道注意力机制,能够提高模型的学习能力且减少参数量;最后,引入K–means++聚类算法对焊接件表面缺陷数据集中待检测的标注框宽高进行聚类,使网络模型更容易检测到样本中的缺陷。结果 实验结果表明,改进后的YOLOv4算法平均精度(mean Average Precision,mAP)为91.07%,检测速度达到48.11帧/s,模型尺寸为43.2 MB,比原始YOLOv4算法平均精度提升了4.61%,检测速度提高了26.59帧/s,模型尺寸缩减了82.37%。结论 所提模型提高了焊接件表面缺陷检测的精度和速度,在工业表面缺陷检测中具有现实意义。     

一种自适应二值化的毫米波图像边缘检测方法

针对毫米波图像分辨率较低、噪声大、成像物体边缘提取困难等问题,提出了一种基于自适应图像二值化的毫米波图像边缘检测方法。该方法通过对图像直方图的分析,自动地确定两个峰值的位置,得出阈值,对图像进行二值化,再对二值化后的图像进行边缘检测。实验表明,这种方法能较好地检测出毫米波图像中人与物体的边缘信息,同时又去掉了大多数由噪声引起的伪边缘。该方法避免了大量的方差计算,计算量仅为大津法的 50%左右,能够满足自适应性和实时性的要求。