Invariant and adaptive geometrical texture features for defect detection and classification

Automatic texture defect detection is highly important for many fields of visual inspection. We introduce novel, geometrical texture features for this task, which are Euclidean motion invariant and texture adaptive: An algebraic function (rational, Padé, or polynomial) is integrated over intensities in local, circular neighborhoods on the image including an anisotropical texture analysis. Adaptiveness is achieved through the optimization of this feature kernel and further coefficients based on a simplex energy minimization, constrained by a measure of texture discrimination (Fisher criterion). A backpropagation trained, multilayer perceptron network classifies the textures locally. Our approach contains new properties, usually not common in feature theories: Theoretically implicit, multiple invariances and an automatic and specific adaptation of the features to the texture images. Experiments with a fabric data set and Brodatz textures reveal up to 98.6% recognition accuracy.     

Wavelet-based defect detection in solar wafer images with inhomogeneous texture

Solar power is an attractive alternative source of electricity. Multicrystalline solar cells dominate the market share owing to their lower manufacturing costs. The surface quality of a solar wafer determines the conversion efficiency of the solar cell. A multicrystalline solar wafer surface contains numerous crystal grains of random shapes and sizes in random positions and directions with different illumination reflections, therefore resulting in an inhomogeneous texture in the sensed image. This texture makes the defect detection task extremely difficult. This paper proposes a wavelet-based discriminant measure for defect inspection in multicrystalline solar wafer images.The traditional wavelet transform techniques for texture analysis and surface inspection rely mainly on the discriminant features extracted in individual decomposition levels. However, these techniques cannot be directly applied to solar wafers with inhomogeneous grain patterns. The defects found in a solar wafer surface generally involve scattering and blurred edges with respect to clear and sharp edges of crystal grains in the background. The proposed method uses the wavelet coefficients in individual decomposition levels as features and the difference of the coefficient values between two consecutive resolution levels as the weights to distinguish local defects from the crystal grain background, and generates a better discriminant measure for identifying various defects in the multicrystalline solar wafers. Experimental results have shown the proposed method performs effectively for detecting fingerprint, contaminant, and saw-mark defects in solar wafer surfaces.     

基于图像识别技术的轨道交通缺陷检测研究

传统人工巡检轨道交通缺陷存在效率低、误差大等缺点,运用综合轨道检查车(CTIV)为检测平台,建立了一种车载式轨道交通图像识别智能巡检系统。利用CTIV采集连续轨道边界框图像建立数据集,在C++中使用应用程序开发框架(QT)设计了可视化数据标注的定制软件工具。通过全卷积网络(FCN)建立了多任务学习扩展网络架构,结合多个...     

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,...     

基于改进部分卷积的瑕疵布匹图像生成算法

针对工业生产中布匹瑕疵自动化检测模型训练时缺少带瑕疵位置信息的瑕疵布匹图像数据集的问题,本文提出了一种以改进的部分卷积网络作为基本框架的带瑕疵位置信息的瑕疵布匹图像生成模型EC-PConv.该模型引入小尺寸瑕疵特征提取网络,将提取出的瑕疵纹理特征与空白mask拼接起来形成带有位置信息和瑕疵纹理特征的mask,然后以修复方式生成带有瑕疵位置信息的瑕疵布匹图像,另外,本文提出一种结合MSE损失的混合损失函数以生成更加清晰的瑕疵纹理.实验结果表明,与最新的GAN生成模型相比,本文提出的生成模型的FID值降低了0.51;生成的瑕疵布匹图像在布匹瑕疵检测模型中查准率P和MAP值分别提高了0.118和0.106.实验结果表明,该方法在瑕疵布匹图像生成上比其他算法更稳定,能够生成更高质量的带瑕疵位置信息的瑕疵布匹图像,可较好地解决布匹瑕疵自动化检测模型缺少训练数据集的问题.     

一种基于纹理特征的笔迹鉴别方法

介绍了一种基于纹理特征的笔迹识别方法。把手写笔迹图像作为一种纹理看待,从而将笔迹识别问题转化为纹理识别问题。笔迹图像预处理采用基于像素点的切割方法,通过实验证明该方法可以较为完整的保存纹理信息。对于预处理后的纹理图像,再利用纹理处理技术和数学方法提取笔迹纹理特征,设计Gabor滤波器对特征图像鉴别,所有过程均使用MATLAB编程仿真实现。试验结果表明采用纹理识别的方法简单,避免了由于文字数量、纸张材质、字体颜色等因素的影响,显著提高了识别的准确度和笔迹识别应用的广度。     

Defect detection in inhomogeneously textured sputtered surfaces using 3D Fourier image reconstruction

Texture analysis techniques have been used extensively for surface inspection, in which small defects that appear as local anomalies in textured surfaces must be detected. Traditional surface inspection methods are mainly concentrated on homogeneous textures. In this paper, we propose a 3D Fourier reconstruction scheme to tackle the problem of surface inspection on sputtered glass substrates that contain inhomogeneous textures. Such sputtered surfaces can be found in touch panels and liquid crystal displays (LCDs). Since an inhomogeneously textured surface does not have repetition, self-similarity properties in the image, a sequence of faultless images along with the inspection image are used to construct a 3D image so that the periodic patterns of the surface can be observed in the additional frame-axis. Bandreject filtering is used to eliminate frequency components associated with faultless textures in the spatial domain image, and the 3D inverse Fourier transform is then carried out to reconstruct the image. The resulting image can effectively remove background textures and distinctly preserve anomalies. This converts the difficult defect detection in complicated inhomogeneous textures into a simple thresholding in nontextured images. Experimental results from a number of sputtered glass surfaces have shown the efficacy of the proposed 3D Fourier image reconstruction scheme.     

A hybrid-based texture synthesis approach

Texture synthesis has been an active research area in computer graphics, vision, and image processing. A hybrid texture synthesis approach that combines the strength of Ashikhmins [1] and Liangs [11] algorithms is presented in this paper. Using patches from the input sample texture to extend the input itself, more suitable valid candidate pixels in the input sample can be more precisely determined. An extra original position array is used to record the valid pixel position in the extended region of input sample texture such that the candidate pixel can be retrieved efficiently. Pasting patches with more global information of texture features to initialize the output texture, the texture synthesis process tends to grow larger pieces in the output texture so that the perceptual similarity is reserved as much as possible. Many classes of textures have been used to test our approach. As the experimental results showed, the proposed hybrid approach effectively and efficiently synthesizes high-quality textures from a wide variety of textures.     

一种基于pix2pix改进的工业缺陷数据增强方法

基于深度学习的目标检测算法在工业检测中应用广泛,为解决工业缺陷数据不足的问题,提出了一种基于pix2pix改进的缺陷数据增强方法。从加强生成器和判别器对图像中缺陷区域的注意力出发,针对pix2pix进行了如下改进：(1)仅将整幅图像的缺陷区域作为判别器的输入,以此提升生成器对缺陷区域的注意力,同时,判别器采用了更小的卷积核提取缺陷区域的特征;(2)仅将图像中所有缺陷区域的平均生成对抗损失作为该图像的生成对抗损失,使网络更加关注缺陷区域的特征学习。在工业LED缺陷数据集上的实验结果表明,本方法生成的缺陷具有更逼真的视觉效果和更低的FID指数,同时有效提升了基于RetinaNet算法的缺陷检测精度。     

基于改进相干增强扩散与纹理能量测度和高斯混合模型的导光板表面缺陷检测方法

针对液晶屏(LCD)导光板表面缺陷检测方法存在漏检率和误检率较高,对产品表面复杂渐变的纹理结构适应性差的问题,提出一种基于改进相干增强扩散(ICED)与纹理能量测度和高斯混合模型(TEM-GMM)的LCD导光板表面缺陷检测方法。首先,构建ICED模型,基于结构张量引入平均曲率流扩散(MCF)滤波,使得相干增强扩散(CED)模型对缺陷的细线状纹理有良好的边缘保持效果,并利用相干性得到缺陷纹理增强和背景纹理抑制的滤波后图像;然后,根据Laws纹理能量测度(TEM)提取图像纹理特征,将图像的背景纹理特征作为离线阶段高斯混合模型(GMM)的训练数据,使用期望最大化(EM)算法估计GMM参数;最后,计算待检测图像各像素的后验概率,并将其作为在线检测阶段缺陷像素的判断依据。实验结果表明,该检测方法在导光颗粒随机、规则两种分布的缺陷图像测试数据组上的漏检率和误检率分别为3.27%、4.32%和3.59%、4.87%。所提检测方法适用范围广,可有效检测出LCD导光板表面划痕、异物、脏污和压伤等类型的缺陷。     

飞行器表面矢量场数据动态纹理可视化方法

面向飞行器表面流场数据可视化的应用需求,提出一种基于线性卷积（LIC）及纹理平流（IBFVS）相结合的动态纹理可视化方法。算法通过将IBFVS方法的背景随机噪声替换为LIC纹理方式,结合了LIC纹理结果对比度高及IBFVS方法生成速度快的优势;针对LIC绘制速度慢的不足,利用GPU对曲面矢量场投影并插值,生成规则矢量数据场;用GPU对LIC部分进行并行加速,有效提高了LIC纹理图像产生速度;将LIC结果图像加入到IBFVS进行平流,生成纹理图像,最后加入颜色映射,丰富流场信息。实验结果表明,该方法生成的飞行器表面动态纹理图像对比度高,清晰度强,实时绘制性能好。     

Texture models and image measures for texture discrimination

The task of texture segmentation is to identify image curves that separate different textures. To segment textured images, one must first be able to discriminate textures. A segmentation algorithm performs texture-discrimination tests at densely spaced image positions, then interprets the results to localize edges. This article focuses on the first stage, texture discrimination.We distinguish between perceptual and physical texture differences: the former differences are those perceived by humans, while the latter, on which we concentrate, are those defined by differences in the processes that create the texture in the scene. Physical texture discrimination requires computing image texture measures that allow the inference of physical differences in texture processes, which in turn requires modeling texture in the scene. We use a simple texture model that describes textures by distributions of shape, position, and color of substructures. From this model, a set of image texture measures is derived that allows reliable texture discrimination. These measures are distributions of overall substructure length, width, and orientation; edge length and orientation; and differences in averaged color. Distributions are estimated without explicitly isolating image substructures. Tests of statistical significance are used to compare texture measures.A forced-choice method for evaluating texture measures is described. The proposed measures provide empirical discrimination accuracy of 84 to 100% on a large set of natural textures. By comparison, Laws' texture measures provide less than 50% accuracy when used with the same texture-edge detector. Finally, the measures can distinguish textures differing in second-order statistics, although those statistics are not explicitly measured.The author was with the Robotics Laboratory, Computer Science Department, Stanford University, Stanford, California 94305. He is now with the Institut National de Recherche en Informatique et en Automatique (INRIA), Sophia-Antipolis, 2004 Route des Lucioles, 06565 Valbonne Cedex, France.     

周期纹理背景中的表面缺陷检测技术

基于机器视觉原理的自动光学表面缺陷检测技术是当今工业生产中在线检测表面缺陷的一种新的技术方法,是精密制造与组装工业过程中保证零部件表面质量的重要检测手段.以液晶面板TFT阵列表面缺陷自动光学检测为例,介绍了表面缺陷自动光学检测的基本组成原理,阐述了周期纹理背景表面上的表面缺陷检测方法、缺陷信息处理的基本过程与实用算法.针对表面缺陷检测图像处理技术难题,详细论述了表面缺陷扫描图像中的周期纹理背景傅里叶变换频域滤波方法、缺陷分割双阈值统计控制法,并用实验结果给出了例证.     

基于Gaussian-yolov3的铝型材表面缺陷检测

在铝型材的实际生产过程中,由于各方面因素的影响,铝型材表面会产生碰伤,刮花,凸粉等瑕疵,这些瑕疵会严重影响铝型材的质量。目前主要采用人工检测,由于铝型材表面自身含有纹路,与瑕疵区分度不高,传统人工肉眼检查十分费力,质检的效果难以控制。为解决上述问题,以铝型材表面缺陷为研究对象,使用Gaussian-yolov3为基础目标检测网络,针对铝型材表面部分条状缺陷的特性,使用变形卷积技术增强卷积的适应性。针对小缺陷检测问题,使用密集连接技术。使用数据增强扩展数据。通过对比Faster R-CNN、SSD实验,结果表明,基于Gaussian-yolov3的检测方法准确率可以达到96%,检测速度可以满足实时性要求,具有较强的实用性。     

基于反向P-M扩散的钢轨表面缺陷视觉检测

研制了一种基于反向P-M（Perona-Malik）扩散的钢轨表面缺陷视觉检测装置,该装置可 自动获取钢轨表面图像,并实现实时检测与定位钢轨表面缺陷. 钢轨图像具有光 照变化、反射不均、特征少等特点,为了在运动过程中 从复杂的钢轨表面图像提取缺陷,首先将图像进行反向P-M扩散,然后将扩散后的图像与原图像进 行差分,从而减小了上述因素的影响,最后将差分图像进行二值化操作,根据 缺陷边缘特性和面积进行滤波,分割出缺陷图像. 实验仿真和现场测试结果表明,该方法能很好地识别块状缺陷和线状缺陷,并且检测速度、精度、识别 率和误检率都能很好地满足要求.     

Multiscale directional filter bank with applications to structured and random texture retrieval

In this paper, multiscale directional filter bank (MDFB) is investigated for texture characterization and retrieval. First, the problem of aliasing in decimated bandpass images on directional decomposition is addressed. MDFB is then designed to suppress the aliasing effect as well as to minimize the reduction in frequency resolution. Second, an entropy-based measure on energy signatures is proposed to classify structured and random textures. With the use of this measure for texture pre-classification, an optimized retrieval performance can be achieved by selecting the MDFB-based method for retrieving structured textures and a statistical or model-based method for retrieving random textures. In addition, a feature reduction scheme and a rotation-invariant conversion method are developed. The former is developed so as to find the most representative features while the latter is developed to provide a set of rotation-invariant features for texture characterization. Experimental works confirm that they are effective for texture retrieval.     

DLSE-Net: A robust weakly supervised network for fabric defect detection

The feasibility of deep convolutional neural network for fabric defect detection has been proven, but the detection performance often depends on large-scale labeled datasets. However, it is troublesome to collect large amounts of fabric defects with pixel-level labeling in industrial production. Although the weakly supervised detection methods can reduce the labeling workload, fabric defect detection is still a challenging task due to the slight difference between defects and complex texture backgrounds, and the diversity of defect types. To alleviate this issue, this paper proposes an effective weakly supervised shallow network, called DLSE-Net, with Link-SE (L-SE) module and Dilation Up-Weight CAM (DUW-CAM) for fabric defect detection. Firstly, the network regards a residual connection as a new branch to alleviate the semantic gap generated by the connection of different layers. Secondly, L-SE module forces the weights to be associated with the overall network in a global optimization manner instead of only within a single layer. Finally, a novel DUW-CAM with an attention mechanism is proposed to improve the adaptability of the network by combining dilated convolution and attention mechanism. Moreover, DUW-CAM can effectively suppress the background and highlight defect regions, even on complex fabric textures. Experimental results demonstrate that our proposed approach can localize the defects with high accuracy, and outperforms the state-of-the-art methods on two distinctive fabric datasets with different textures.     

An evolutionary system for near-regular texture synthesis

Near-regular texture is probably among the most difficult to handle in the texture synthesis area, because the synthesis must preserve the holistic structural property and the local randomness simultaneously. In this paper, motivated by the relationship between a near-regular texture image and an evolutionary system, we propose a novel texture synthesis algorithm. By defining individuals with appropriate attributes and behaviors, we convert the texture synthesis problem to an evolution process of an evolutionary system. It can achieve high-quality synthesized results on a large variety of near-regular textures without any extra overhead for memory and pretreatment, and the speed approaches real-time. Moreover, it can be easily generalized to deal with other kinds of textures.     

Affine invariant classification and retrieval of texture images

In this paper, we propose a new method of extracting affine invariant texture signatures for content-based affine invariant image retrieval (CBAIR). The algorithm discussed in this paper exploits the spectral signatures of texture images. Based on spectral representation of affine transform, anisotropic scale invariant signatures of orientation spectrum distributions are extracted. Peaks distribution vector (PDV) obtained from signature distributions captures texture properties invariant to affine transform. The PDV is used to measure the similarity between textures. Extensive experimental results are included to demonstrate the performance of the method in texture classification and CBAIR.     

TEXEMS: texture exemplars for defect detection on random textured surfaces

We present an approach to detecting and localizing defects in random color textures which requires only a few defect free samples for unsupervised training. It is assumed that each image is generated by a superposition of various-size image patches with added variations at each pixel position. These image patches and their corresponding variances are referred to here as textural exemplars or texems. Mixture models are applied to obtain the texems using multiscale analysis to reduce the computational costs. Novelty detection on color texture surfaces is performed by examining the same-source similarity based on the data likelihood in multiscale, followed by logical processes to combine the defect candidates to localize defects. The proposed method is compared against a Gabor filter bank-based novelty detection method. Also, we compare different texem generalization schemes for defect detection in terms of accuracy and efficiency.