印制电路板缺陷图像边缘检测

为了提取含噪声印制电路板(PCB)光板缺陷图像边缘信息,提出了一种基于混合法的图像边缘检测方法.在分析类间最大距离法图像分割基本原理的基础上提出了一种改进的类间最大距离法(IMDBC);设计了结合中值滤波、IMDBC、改进的数学形态学边缘检测算子与LOG算子进行PCB光板缺陷图像边缘检测的混合方法.用CCD及显微镜成像系统获取4幅PCB光板缺陷图像,结果表明:用本文方法提取出的图像边缘信息清晰且较精确,噪声点较少,所得到的4幅图像优质系数是其它6种方法的1.0111~1.3586倍.     

基于机器视觉的车辆保险盒在线检测研究

摘要: 车辆保险盒作为汽车电控系统中的一个重要的元器件,其质量好坏直接影响汽车的性能,传统的车辆保险盒检测主要依靠人工检测,检测费时费力,针对该问题,提出一种基于视觉的车辆保险盒在线检测方法,分析了产品图像校正到标准模板图像的位置误差,采用SURF(Speeded Up Robust Feature)算法和平面单应性理论将待检产品图像变换到标准模板位置,利用颜色直方图匹配和模板匹配完成保险盒上元件的检测。实验结果证明,该方法检测效率高,稳定可靠,能够满足在线检测的要求,具有一定实用价值。     

改进强度映射函数的多尺度曝光图像融合

针对多曝光图像融合中的鬼影问题,提出了一种改进强度映射函数的多尺度曝光图像融合算法.基于参考帧图像分别确定输入帧的高低对比度;采用高对比度区域进行结构一致性检测得出鬼影区域;利用改进后的基于强度映射关系的能量函数进一步检测低对比度区域的鬼影信息;利用多尺度块匹配算法进行快速融合.实验结果表明,与已有的代表性方法相比,该...     

连续帧间差分与背景差分相融合的运动目标检测方法

为了克服背景差分法和帧间差分法的不足,有效提高运动目标检测的准确性、实时性和检测效率,提出了一种将连续帧间差分法与背景差分法相结合的运动目标检测方法.首先通过连续帧间差分法获得连续帧差图像,然后分别通过线性的自适应滤波、非线性的中值滤波获得背景图像进行差分,之后再利用阈值分割技术实现运动目标的增强,从而有效解决背景差分法和帧间差分法中都可能出现的无法检测目标的现象.实验表明,该算法可以有效避免漏检、误检等情况,提高运动目标检测的效率和准确性.     

基于机器视觉的电机换向器质量在线检测系统开发

电机换向器质量检测是换向器生产线中的一个重要工序,但其仍采用人工方式,存在检测效率低、漏检率高等问题。针对此问题,本文运用图像处理和机器视觉技术,开发换向器质量在线视觉检测系统。该系统针对生产过程工艺多变,造成形状检测标准不一致问题,提出自适应学习模板方法;在轴孔孔径检测,提出基于Freeman链码改进的孔径快速检测算法;在端面缺陷中,提出基于改进视觉注意力模型的端面缺陷检测方法。实验结果表明,系统检测精度达到99.80%,漏检率为0%,F-measure值为99.89%。该系统能够快速有效检测换向器存在的外观质量问题,可满足换向器在线质量检测需求。     

TOFD图像时域解混叠的自适应匹配追踪方法*

当TOFD检测的时域分辨率不足时,小缺陷的上下端点衍射波会出现时域混叠,难以准确判断缺陷性质及测量缺陷高度。为解决此问题,提出了自适应匹配追踪算法,该算法利用主成分分析法从检测图像中提取匹配追踪原子,根据散射规律生成字典,通过正交匹配追踪算法实现对时域混叠信号的分离,并使用投影矢量重新成像,实现对缺陷上下端点的有效区分。该方法能够改进TOFD技术在小缺陷测高方面的不足,试验证明,该方法对薄板对接接头中高度为1.80 mm的埋藏缺陷测量误差小于0.30 mm。     

基于逻辑回归的匹配滤波器设计方法

针对遥感相机常规采样图像的目标检测问题,提出了基于逻辑回归的匹配滤波器设计方法。针对不同的图像目标特征,充分分析常规采样后图像上目标点的特征,选择全面且适合的学习样本;考虑到所获得的图像内混入杂波和噪声,因此,采用最大化信杂噪比作为逻辑回归算法的性能指标,实现匹配滤波模板的迭代优化。对比加入匹配滤波器前后目标临域内的信杂噪比,并将优化的匹配滤波器与文献中的最优滤波器相比,试验证明与文献中的滤波器相比,优化的匹配滤波器在目标检测方面更加有效。     

多联融合优化模板匹配的纱纸管分类方法

圆锥纱纸管的自动分类识别一直是该部件智能制造方面的技术难题,针对传统图像分类方法无法兼顾速度与精度,以及深度学习成本大、部署难、硬件要求高等问题,提出了一种基于多联融合优化模板匹配的纱纸管分类方法。采用多个改进算法及策略并使用三次数据降维加快模板匹配速度。将用于运动估计的优化算法SEA(successive elimination algorithm)用于模板匹配中,并把该算法的阈值改进为自适应阈值,用于加强算法鲁棒性;采用小波金字塔进行数据降维,减少运算量并提高运算速度;最后采用十字灰度特征模板代替传统SAD(sum of absolute differences)算法及其模板计算性能指标,并采用提前停止迭代搜索的策略进一步滤除数据,设置累计误差阈值来提前停止搜索。匹配实验表明,本文的改进算法保证了精度,并且匹配速度达到了0.126 s左右;对比、消融实验表明,本文算法在保证了精度的前提下,速度比传统SAD算法提升了近11倍,相比于一些其他经典的方法在速度上也均有提升,证明了该方法的有效性。     

基于变换矩阵的BGA X-ray图像倾斜识别

针对基于X-Ray的焊球阵列封装(BGA)焊接缺陷检测中,现有的图像处理算法无法有效处理PCB意外倾斜的问题,提出了一种自动判断BGA焊点X射线图像倾斜程度并进行校正的方法。首先根据BGA焊点阵列排布的特性恢复出原始图像中的结构信息,然后使用广义逆矩阵求解出理想正视图像与实际倾斜图像之间的变换矩阵,最后对倾斜图像进行逆变换以得到理想正视图像,并使用变换矩阵估计出PCB的倾斜程度。实验针对正视与倾斜的BGA焊点的X射线图像,运用所提方法,准确判别出图像的倾斜程度,并进行了校正。此方法既可以作为一种图像质量评价算法,在BGA X-Ray缺陷检测中判断图像是否为需要的正视图像;也可以作为一种图像自动校正算法,提升基于X射线的自动检测系统的适应性。     

以道缝为参考的路面检测车定位方法研究

针对有道缝路面提出了一种以道缝为参考的路面检测车自身定位方法。该方法通过数字CCD相机采集路面图像,提取出道缝信息,并选取十字交叉道缝为模板进行模板匹配实现定位。用Labview及IMAQ Vision编写了定位程序,模拟实验证明该方法能够实现对路面检测车的准确定位。     

基于模板匹配法的枪械射击准确度验收系统

枪械射击准确度是枪械验收的一项重要指标。为提高验收精度、降低验收成本,针对现有验收方法的不足,提出了光电成像并结合图像处理的验收方法。根据成像的图像特点和验收的实际要求,采用模板匹配算法识别代表瞄准线的十字分划,拟合枪管轴线并用十字分划表示,通过检验两十字之间的角度关系来进行射击准确度的验收。研究结果表明,采用模板匹配算法,十字分划的识别精度小于1个像素,射击准确度验收系统的精度约为0.26 mil。     

高精度自动贴片机视觉系统定位算法研究

针对高精度自动贴片机的关键技术视觉识别定位算法进行了研究,针对贴片机PCB板标记点及元件图像的特点,提出了结合图像分割、几何特征识别与模式匹配的图像识别及定位方法。根据以上算法开发了针对视觉定位系统的图像识别软件,并用PCB板图像及元件图像进行识别定位验证。实验结果表明,该算法能够有效地完成贴片机视觉系统的识别定位任务。     

基于Fourier-Mellin变换的气象卫星光谱图像配准

气象卫星光谱图像是气象科学和环境遥感科学研究的重要工具,而图像配准是气象卫星图像数据应用的前提。文章针对气象卫星光谱图像的配准问题,提出了一种基于Fourier-Mellin变换的自动配准方法。首先利用全球海岸线矢量图数据构造地标模板,地标模板是气象卫星光谱图像配准的参考图像;其次,根据云通道数据选择无云区域红外子图像,并利用Sobel算子对红外光谱图像提取边缘特征;最后利用Fourier-Mellin变换确定地标模板图像和红外边缘图像之间的仿射变换参数,从而实现红外光谱图像的配准。该方法本质是基于曲线匹配的思想,无需特征点提取,大大简化了配准流程。利用FY-2D气象卫星上获取的红外通道数据进行了实验,结果表明：该方法鲁棒性好,运算速度快,配准精度较高。     

A coarse-to-fine kernel matching approach for mean-shift based visual tracking

Mean shift is an efficient pattern match algorithm. It is widely used in visual tracking fields since it need not perform whole search in the image space. It employs gradient optimization method to reduce the time of feature matching and realize rapid object localization, and uses Bhattacharyya coefficient as the similarity measure between object template and candidate template. This thesis presents a mean shift algorithm based on coarse-to-fine search for the best kernel matching. This paper researches for object tracking with large motion area based on mean shift. To realize efficient tracking of such an object, we present a kernel matching method from coarseness to fine. If the motion areas of the object between two frames are very large and they are not overlapped in image space, then the traditional mean shift method can only obtain local optimal value by iterative computing in the old object window area, so the real tracking position cannot be obtained and the object tracking will be disabled. Our proposed algorithm can efficiently use a similarity measure function to realize the rough location of motion object, then use mean shift method to obtain the accurate local optimal value by iterative computing, which successfully realizes object tracking with large motion. Experimental results show its good performance in accuracy and speed when compared with background-weighted histogram algorithm in the literature.     

Track infrared point targets based on projection coefficient templates and non-linear correlation combined with Kalman prediction

For a long time, tracking IR point targets is a great challenge task. We propose a tracking framework based on template matching combined with Kalman prediction. Firstly, a novel template matching method for detecting infrared point targets is presented. Different from the classic template matching, the projection coefficients obtained from principal component analysis are used as templates and the non-linear correlation coefficient is used to measure the matching degree. The non-linear correlation can capture the higher-order statistics. So the detection performance is improved greatly. Secondly, a framework of tracking point targets, based on the proposed detection method and Kalman prediction, is developed. Kalman prediction reduces the searching region for the detection method and, in turn, the detection method provides the more precise measurement for Kalman prediction. They bring out the best in each other. Results of experiments show that this framework is competent to track infrared point targets.     

A Study on Railway Surface Defects Detection Based on Machine Vision

The detection of rail surface defects is an important tool to ensure the safe operation of rail transit. Due to the complex diversity of track surface defect features and the small size of the defect area, it is difficult to obtain satisfying detection results by traditional machine vision methods. The existing deep learning-based methods have the problems of large model sizes, excessive parameters, low accuracy and slow speed. Therefore, this paper proposes a new method based on an improved YOLOv4 (You Only Look Once, YOLO) for railway surface defect detection. In this method, MobileNetv3 is used as the backbone network of YOLOv4 to extract image features, and at the same time, deep separable convolution is applied on the PANet layer in YOLOv4, which realizes the lightweight network and real-time detection of the railway surface. The test results show that, compared with YOLOv4, the study can reduce the amount of the parameters by 78.04%, speed up the detection by 10.36 frames per second and decrease the model volume by 78%. Compared with other methods, the proposed method can achieve a higher detection accuracy, making it suitable for the fast and accurate detection of railway surface defects.     

改进Fast-RCNN的双目视觉车辆检测方法

针对不同空间尺度的车辆表现出显著不同的特征导致检测算法效率低、准确性差且单目难以准确获取车辆距离信息的问题,提出了一种改进Fast-RCNN的汽车目标检测法,利用双目视觉对车辆进行测距。首先利用双目立体相机采集前方图像并进行预处理,加载深度神经网络Fast-RCNN的训练数据,再针对汽车不同空间尺度引入多个内置的子网络,将来自所有子网络的输出自适应组合对车辆进行检测,然后利用SURF特征匹配算法进行左右图像的立体匹配,根据匹配数据进行三维重建并确定车辆质心坐标,从而测量出车辆与双目相机之间的距离。实验结果表明,所述算法可以实现对车辆的快速检测,检测时间比传统的Fast-RCNN缩短了42 ms,并且实现了对5 m范围车辆距离的准确测量,其误差仅为2.4%,精确度高,实时性好。     

基于自适应阈值的齿轮干涉图像前景区域提取方法

齿面物体像灰度法是激光移相干涉测量中提取齿轮干涉图像前景区域的重要方法之一,针对该方法因人工设定阈值且忽略不同图像边缘特征从而导致的测量效率及精度受限问题,提出了一种基于自适应阈值的齿轮干涉图像前景区域提取方法。首先分析齿轮齿面形貌特征与各边缘顶点差异,对图像进行区域划分;然后根据边缘灰度变化规律通过邻域窗口筛选合格像素点并获取掩模结果,实现前景区域提取;最后根据5类图像评价指标分别对4组算法分割结果与传统方法分割结果进行数据对比。结果表明：算法在实现图像自动处理的基础上与参考结果匹配精确度提升约3.5%～4.5%,PRI(probabilistic rand index)提升约3%～4%,VOI(variation of information)提高约15%～25%,GCE(global consistency error)降低约2.5%～3.5%,最终相位信息准确度提升9μm～15μm。结果符合精度要求,该方法可广泛应用于齿轮干涉图像前景提取中。     

基于区域协方差的惯性组合导航景象匹配算法

 针对景象匹配辅助惯性组合导航系统需要快速准确获取飞行器位置和航向偏差的要求,提出了一种基于区域协方差的实时图像匹配算法.算法采用区域协方差矩阵的距离作为图像匹配时的相似性度量.首先,对图像进行高斯平滑滤波,提取图像的多种特征计算区域协方差矩阵,利用金字塔多级匹配技术进行全局搜索,获得测试图在参考图中像素级匹配位置.然后,利用全局匹配的结果,在实测图上选取多个局部区域,分别进行局部搜索匹配,获取参考图和实测图中一一对应的局部匹配集.最后,利用RANSAC算法和最小二乘算法计算出两幅图像间的最优相似变换参量.仿真分析表明,该算法能满足景象匹配辅助惯性组合导航系统实时性、精确性和鲁棒性的要求.     

Automated inspection of micro-defect recognition system for color filter

This study focused on micro-defect recognition and classification in color filters. First, six types of defects were examined, namely grain, black matrix hole (BMH), indium tin oxide (ITO) defect, missing edge and shape (MES), highlights, and particle. Orthogonal projection was applied to locate each pixel in a test image. Then, an image comparison was performed to mark similar blocks on the test image. The block that best resembled the template was chosen as the new template (or matching adaptive template). Afterwards, image subtraction was applied to subtract the pixels at the same location in each block of the test image from the matching adaptive template. The control limit law employed logic operation to separate the defect from the background region. The complete defect structure was obtained by the morphology method. Next, feature values, including defect gray value, red, green, and blue (RGB) color components, and aspect ratio were obtained as the classifier input. The experimental results showed that defect recognition could be completed as fast as 0.154 s using the proposed recognition system and software. In micro-defect classification, back-propagation neural network (BPNN) and minimum distance classifier (MDC) served as the defect classification decision theories for the five acquired feature values. To validate the proposed system, this study used 41 defects as training samples, and treated the feature values of 307 test samples as the BPNN classifier inputs. The total recognition rate was 93.7%. When an MDC was used, the total recognition rate was 96.8%, indicating that the MDC method is feasible in applying automatic optical inspection technology to classify micro-defects of color filters. The proposed system is proven to successfully improve the production yield and lower costs.