Defect detection in patterned wafers using anisotropic kernels

Wafer defect detection often relies on accurate image registration of source and reference images obtained from neighboring dies. Unfortunately, perfect registration is generally impossible, due to pattern variations between the source and reference images. In this paper, we propose a defect detection procedure, which avoids image registration and is robust to pattern variations. The proposed method is based on anisotropic kernel reconstruction of the source image using the reference image. The source and reference images are mapped into a feature space, where every feature with origin in the source image is estimated by a weighted sum of neighboring features from the reference image. The set of neighboring features is determined according to the spatial neighborhood in the original image space, and the weights are calculated from exponential distance similarity function. We show that features originating from defect regions are not reconstructible from the reference image, and hence can be identified. The performance of the proposed algorithm is evaluated and its advantage is demonstrated compared to using an anomaly detection algorithm.     

A cluster-based wavelet feature extraction method and its application

In this paper, a new cluster-based approach is proposed for extracting features from the coefficients of a two-dimensional discrete wavelet transform. The wavelet coefficients from the matrix of each frequency channel are segregated into non-overlapping clusters in an unsupervised mode using a set of application-specific representative images. In practical situations, this set of representative images can be the same as the ones kept aside for training a classifier. The proposed method divides the matrices of computed wavelet coefficients into disjoint clusters that are centered around the position of dominant coefficients. The features that can distinguish images of one class from those of other classes are obtained by computing energies of the clusters. The feature vectors so obtained are then presented as input patterns to an image classifier, such as a neural network. Experimental results based on the applications for texture classification and wood surface defect detection have shown that the proposed cluster-based wavelet feature extraction method is able to effectively extract important intrinsic information content from the test images, and increase the overall classification accuracy as compared with conventional feature extraction methods.     

An efficient similarity measure approach for PCB surface defect detection

In this paper, an efficient similarity measure method is proposed for printed circuit board (PCB) surface defect detection. The advantage of the presented approach is that the measurement of similarity between the scene image and the reference image of PCB surface is taken without computing image features such as eigenvalues and eigenvectors. In the proposed approach, a symmetric matrix is calculated using the companion matrices of two compared images. Further, the rank of a symmetric matrix is used as similarity measure metric for defect detection. The numerical value of rank is zero for the defectless images and distinctly large for defective images. It is reliable and well tolerated to local variations and misalignment. The various experiments are carried out on the different PCB images. Moreover, the presented approach is tested in the presence of varying illumination and noise effect. Experimental results have shown the effectiveness of the proposed approach for detecting and locating the local defects in a complicated component-mounted PCB images.     

针对重复模式图像的成对特征点匹配

目的 含有重复模式的图像会对局部特征描述符产生歧义,因此基于局部特征的匹配算法在此类图像的匹配过程中极易产生误匹配.同时,通过研究现有的引入全局特征描述符的匹配算法,发现全局特征同样依赖于计算局部信息所得到的特征点主方向,所以此类方法在含有重复模式的图像中也不容易得到令人满意的匹配效果.为了解决这一问题,提出一种基于成对特征点的图像匹配算法.方法 该方法利用成对特征点的方向向量作为特征点对的主方向,为特征描述提供了正确的方向信息,同时引入DAISY描述符与改进后的全局上下文(globalcontext)特征描述符,提高了匹配能力.结果 分别在模拟图像与实际图像上面进行了对比匹配实验,本文算法平均的匹配正确率能达到88％以上,比其他经典的匹配算法提高了26％以上.结论 实验结果表明,本文算法克服了现有算法在特征描述与主方向分配上的缺陷,进一步提升了匹配正确率,能够有效地解决重复模式图像的匹配问题.     

Feature matching based on unsupervised manifold alignment

Feature-based methods for image registration frequently encounter the correspondence problem. In this paper, we formulate feature-based image registration as a manifold alignment problem, and present a novel matching method for finding the correspondences among different images containing the same object. Different from the semi-supervised manifold alignment, our methods map the data sets to the underlying common manifold without using correspondence information. An iterative multiplicative updating algorithm is proposed to optimize the objective, and its convergence is guaranteed theoretically. The proposed approach has been tested for matching accuracy, and robustness to outliers. Its performance on synthetic and real images is compared with the state-of-the-art reference algorithms.     

基于通道间相关性的图像重着色检测

图像重着色是一种新兴的图像编辑技术,通过篡改像素值达到改变图像颜色风格的目的。随着社交网络和图像编辑技术的快速发展,重着色图像已经严重阻碍了信息传达的真实性。然而,专门为重着色而设计的工作少之又少,现有的重着色检测方法在传统重着色场景下仍有很大提升空间,在应对手工重着色图像时效果不佳。为此,提出了一种基于通道间相关性的重着色图像检测方法,该方法适用于重着色任务中的传统重着色和手工重着色场景。基于相机成像和重着色图像生成方式之间存在显著差异这一现象,提出重着色操作或许会破坏自然图像的通道间相关性这一假设。通过数值分析说明,通道间相关性差异可作为区分重着色图像和自然图像的重要鉴别度量。基于上述先验知识,所提方法通过提取差分图像的一阶微分残差的通道共生矩阵,获得图像的通道间相关性特征集。此外,根据实际情况,假设了3种检测场景,包括训练-测试数据之间匹配、不匹配以及手工重着色场景。实验结果表明,所提方法能够准确识别重着色图像,在假设的3种场景下均优于现有方法,取得了较高的检测精度。除此之外,所提方法对训练数据量的依赖性较小,在训练数据有限的情况下,能实现相当精确的预测结果。     

基于多时相巡检图像的变电设备抗干扰缺陷检测

近年来,变电站中广泛采用机器视觉算法分析多时相巡检图像的差异变化,用于检测各类变电设备缺陷,以确保运行安全.然而,由于拍摄时刻不同,多时相图像间存在天气、光照、季节等各类干扰变化,对变电设备的缺陷检测提出了挑战.对此,提出一种基于多时相巡检图像的变电设备抗干扰缺陷检测方法.首先,利用风格迁移模型CycleGAN学习不同风格域之间的映射关系,并基于检测图生成足量存在天气、光照、季节干扰变化的干扰图;其次,基于参考图$+$检测图$+$干扰图三元组对三重孪生网络TripleNet进行协同训练,在特征层面提出空间一致性损失以抵抗各类干扰变化,用于提取三者鲁棒的多尺度差异特征;最后,搭建特征聚合网络PANet融合多尺度差异特征,输出多尺度的缺陷检测结果.在实际变电设备多时相巡检图像数据集上进行实验验证,结果表明,所提出方法相较于非孪生网络和一般孪生网络可提升2.09%和0.67%的mAP,且在原始样本与干扰样本上的检测精度更均衡,而且所提出方法可以在提升变电设备缺陷检测模型精度的同时增强模型的抗干扰能力.     

基于缺陷比例限制的背景差分钢轨表面缺陷检测方法

针对钢轨表面图像具有的光照不均匀、可识别特征有限、对比度低、反射特性易变等特性,提出基于缺陷比例限制的背景差分钢轨表面缺陷检测方法。该方法主要包括轨面图像预处理、背景建模与差分、缺陷比例限制滤波、缺陷比例限制最大熵阈值分割和连通区域标记5个步骤。首先结合轨面图像列灰度均值和列灰度中值进行快速背景建模,将预处理后的图像与背景图像进行差分操作;其次利用轨面图像缺陷占比较低的特征对差分图进行缺陷比例上限的阈值截断,以增强差分图的对比度;随后利用此特征改进最大熵阈值分割,采用自适应加权因子对目标熵进行全局可变加权,并选择出一个合适的阈值使熵值最大化,使得在保留真实缺陷的同时减弱诸如阴影、锈迹等噪声的干扰;最后利用连通区域标记法对阈值分割后的二值图像中的缺陷区域进行统计,并把缺陷面积低于钢轨损伤标准的区域判定为噪声并进行去除,以实现钢轨表面缺陷检测。仿真实验结果表明,新方法可以对钢轨表面缺陷进行很好的检测,其检测结果的召回率、精确率和加权调和平均值分别达到94.19%、88.34%和92.96%,平均错误分类误差值为0.006 4,具有一定的实用价值。     

基于缺陷比例限制的背景差分钢轨表面缺陷检测方法

针对钢轨表面图像具有的光照不均匀、可识别特征有限、对比度低、反射特性易变等特性，提出基于缺陷比例限制的背景差分钢轨表面缺陷检测方法。该方法主要包括轨面图像预处理、背景建模与差分、缺陷比例限制滤波、缺陷比例限制最大熵阈值分割和连通区域标记5个步骤。首先结合轨面图像列灰度均值和列灰度中值进行快速背景建模，将预处理后的图像与背景图像进行差分操作；其次利用轨面图像缺陷占比较低的特征对差分图进行缺陷比例上限的阈值截断，以增强差分图的对比度；随后利用此特征改进最大熵阈值分割，采用自适应加权因子对目标熵进行全局可变加权，并选择出一个合适的阈值使熵值最大化，使得在保留真实缺陷的同时减弱诸如阴影、锈迹等噪声的干扰；最后利用连通区域标记法对阈值分割后的二值图像中的缺陷区域进行统计，并把缺陷面积低于钢轨损伤标准的区域判定为噪声并进行去除，以实现钢轨表面缺陷检测。仿真实验结果表明，新方法可以对钢轨表面缺陷进行很好的检测，其检测结果的召回率、精确率和加权调和平均值分别达到94.19%、88.34%和92.96%，平均错误分类误差值为0.006 4，具有一定的实用价值。     

基于轻量化重构网络的表面缺陷视觉检测

基于深度学习的方法在某些工业产品的表面缺陷识别和分类方面表现出优异的性能,然而大多数工业产品缺陷样本稀缺,而且特征差异大,导致这类需要大量缺陷样本训练的检测方法难以适用.提出一种基于重构网络的无监督缺陷检测算法,仅使用容易大量获得的无缺陷样本数据实现对异常缺陷的检测.提出的算法包括两个阶段:图像重构网络训练阶段和表面缺陷区域检测阶段.训练阶段通过一种轻量化结构的全卷积自编码器设计重构网络,仅使用少量正常样本进行训练,使得重构网络能够生成无缺陷重构图像,进一步提出一种结合结构性损失和L1损失的函数作为重构网络的损失函数,解决自编码器检测算法对不规则纹理表面缺陷检测效果较差的问题;缺陷检测阶段以重构图像与待测图像的残差作为缺陷的可能区域,通过常规图像操作即可实现缺陷的定位.对所提出的重构网络的无监督缺陷检测算法的网络结构、训练像素块大小、损失函数系数等影响因素进行了详细的实验分析,并在多个缺陷图像样本集上与其他同类算法做了对比,结果表明重构网络的无监督缺陷检测算法有较强的鲁棒性和准确性.由于重构网络的无监督缺陷检测算法的轻量化结构,检测1 024×1 024像素图像仅仅耗时2.82 ms,...     

A supervised approach for automated surface defect detection in ceramic tile quality control

Surface defect detection is very important to guarantee the quality of ceramic tiles production. At present, this process is usually performed manually in the ceramic tile industry, which is low efficiency and time-consuming. For small surface defects detection of high-resolution ceramic tiles image, an intelligent detection method for surface defects of ceramic tiles based on an improved you only look once version 5 (YOLOv5) algorithm is presented. Firstly, the high-resolution ceramic tile images are cropped into slices, and the Bottleneck module in the YOLOv5s network is optimized by introducing depthwise convolution and replaced in the whole network. Then, feature extraction is performed using the improved Shufflenetv2 backbone, and an attention mechanism is added to the backbone network to improve the feature extraction ability. The path aggregation network (PAN) and Feature Pyramid Networks (FPN) neck are used to enhance the feature extraction, and finally, the YOLO head is used to identify and locate the ceramic tile defects. The multiple sliding windows detection method is proposed to detect the original ceramic tile image which is faster than the single sliding window detection method. The experimental results show that compared with the original YOLOv5s detection algorithm, the parameters of the model are reduced by 20.46 %, the floating point operations are reduced by 26.22 %, and the mean average precision (mAP) of the proposed method is 96.73 % in the ceramic tile image slice test set which has 1.93 % improvement in mAP than the original YOLOv5s. Compare with other object detection methods, the method proposed in this paper also has certain advantages. In the high-resolution ceramic tile images test set, the mAP of the proposed algorithm is 86.44 % by using the multiple sliding window detection method. The ceramic defect detection experiment has verified the feasibility of the method proposed in this paper.     

A robust method for alignment of histological images

Determination of reference points is a precondition for reconstruction of serial sections. In the case of comprehensive reconstruction work, manual extraction of the markers may be very time-consuming and may even make such reconstruction impossible. The procedure presented in this contribution allows automatic alignment of histological preparations provided that nuclei or comparable structures extend over several sections and are capable of being extracted using methods of pattern recognition. The method was applied to 50 sections with Nissl staining. The nuclei were extracted from the images and evaluated by application of the algorithm. All image pairs were correctly aligned. An integrated control mechanism ensures automatic detection of incorrectly aligned images.     

基于TI-SPCA的人脸自动对齐及识别框架

随着人脸识别算法在众多应用领域的迅猛发展,作为人脸检测和人脸识别中间步骤的人脸对齐算法日益受到重视。针对平面内的人脸图像旋转问题,提出一个基于TI-SPCA（Transformation Invariant Symmetrical Principal Components Analysis）的人脸自动对齐方法及其识别框架。不同于传统的人眼对齐方法,TI-SPCA通过最小化重构图像和扭曲图像之间的误差得到一个旋转不变的特征空间,最终实现无人为干涉的全自动对齐。为了将其性能与人眼对齐方法的性能进行比较,并展示其优势,文中分别在ORL数据库和FERET数据库上通过两种不同对齐方法的输出图像从视觉效果上直观地展现。进一步地,为了验证对齐后的图像在识别算法中的有效性,结合三种距离函数和四种局部算子进行了对比实验,实验结果表明了基于TI-SPCA的全自动对齐方法在人脸识别中的有效性。     

Improved segmentation of semiconductor defects using area sieves

This paper aims at investigating a novel non-referential solution to the problem of defect detection on semiconductor wafer-die images. The suggested solution focuses on segmenting defects from the images using wavelet transformation and morphology-related properties of the associated wavelet coefficients. More specifically, a novel methodology is investigated for segmenting defects by applying an area sieves technique to innovative multidimensional wavelet-based features. These features are extracted from the original defective image using the non-reference K-Level 2-D DWT (Discrete Wavelet Transform). The results of the proposed methodology are illustrated in defective die images where the defective areas are segmented with higher accuracy than the one obtained by applying other reference-based feature extraction methodologies. The first uses all the wavelet coefficients derived from the K-Level 2-D DWT, while the second one uses area sieves to segment the defective regions. Both methods involve in the same classification stage as the proposed feature extraction approach. The promising results obtained outline the importance of judicious selection and processing of 2-D DWT wavelet coefficients for industrial pattern recognition applications.     

Pixel distribution shifting color correction for digital color images

This paper is concerned with a proposed color correction method called the Pixel Distribution Shifting Color Correction (PDSCC). This method employs a shifting process on the pixel distribution of a color image to correct its white reference point and ensure the white reference point is achromatic. The proposed method has been tested on numerous types of images which include indoor, outdoor, and underwater images. The qualitative and quantitative analyses have shown ample evidence that the proposed method outperforms some state-of-the-art methods, such as the Grey World, the White Patch and the General Grey World methods. The resultant images are viewed to be more natural and suggest more pleasant visualization without the intervention of the saturation problem.     

一种印刷电路板缺陷图像边缘信息提取方法

为了较好地提取印刷电路板缺陷图像边缘信息,提出了基于二阶曲线拟合、模式聚类与阈值比较法相结合的印刷电路板缺陷图像边缘信息提取方法。首先分析了最小二乘法拟合的基本原理;然后在此基础上提出了采用二阶曲线拟合法来设定阈值进行拟合得到大致的图像边缘,并分析了其基本原理;最后在模式聚类基础上利用阈值比较法选择适当阈值截取拟合曲线得到图像边缘点、去除噪声边缘点,连接各个图像边缘点可得到缺陷图像的边缘信息。用由显微镜及CCD获取的4幅印刷电路板缺陷图像进行了实验;从实验主观效果看,用该方法提取出图像边缘信息的效果较好,图像边缘比较连续,噪声点极少;从实验客观效果评价看,用该方法所得到的图像边缘信息熵较大。实验结果表明,该方法结合了二阶曲线拟合、模式聚类与阈值比较法优点,可较好地提取出印刷电路板缺陷图像的边缘信息。     

Robust scale invariant target detection using the scale-space theory and optimization for IRST

This paper presents a new small target detection method using scale invariant feature. Detecting small targets whose sizes are varying is very important to automatic target detection in infrared search and track (IRST). The conventional spatial filtering methods with fixed sized kernel show limited target detection performance for incoming targets. The scale invariant target detection can be defined as searching for maxima in the 3D (x, y, and scale) representation of an image with the Laplacian function. The scale invariant feature can detect different sizes of targets robustly. Experimental results with real FLIR images show higher detection rate and lower false alarm rate than conventional methods. Furthermore, the proposed method shows very low false alarms in scan-based IR images than conventional filters.     

基于局部最优分析的纺织品瑕疵检测方法

针对复杂的含有周期变化图案的纺织品瑕疵检测,提出改进Markov随机场模型的无监督纺织品瑕疵检测方法.应用随机场实现周期性纺织品图像的瑕疵检测,利用Markov邻域特性,综合判断瑕疵区域.结合周期图像分割,确定Markov随机场最小图像块计算单元,降低算法的计算复杂度.在随机场势函数定义中,综合考虑相邻图像块的差异特性,结合Markov随机场的全局性判断瑕疵点的位置.引入模糊相似关系矩阵概念,求解改进后的模型参数,使所有图像块的局部能量达到最优.实验表明,文中方法对样本的查全率较高.     

A palm vein identification system based on Gabor wavelet features

As a new and promising biometric feature, thermal palm vein pattern has drawn lots of attention in research and application areas. Many algorithms have been proposed for authentication since palm vein has special characteristics, such as liveness detection and hard to forgery. However, the detection accuracy of palm vein quite depends on the preprocessing and feature representation, which is supposed to be translation and rotation invariant to some extent. In this paper, we proposed an effective method for palm vein identification based on Gabor wavelet features which contains five steps: image acquisition, ROI detection, image preprocessing, features extraction, and matching. The 178 palm vein images from 101 persons were used to test the proposed palm vein recognition approach, where 176 images were correctly recognized with two in failure. The experimental results demonstrate the effectiveness of the proposed approach.