Monitoring defects of ceramic tiles using fuzzy subtractive clustering-based system identification method

In this paper, a subtractive clustering fuzzy identification method and a Sugeno-type fuzzy inference system are used to monitor tile defects in tile manufacturing process. The models for the tile defects are identified by using the firing mechanical resistance, water absorption, shrinkage, tile thickness, dry mechanical resistance and tiles temperature as input data, and using the concavity defect and surface defects as the output data. The process of model building is carried out by using subtractive clustering in both the input and output spaces. A minimum error model is developed through exhaustive search of clustering parameters. The fuzzy model obtained is capable of predicting the tile defects for a given set of inputs as mentioned above. The fuzzy model is verified experimentally using different sets of inputs. This study intends to examine and deal with the experimental results obtained during various stages of ceramic tile production during 90-day period. It is believed, that the results obtained from the present study could be considered in other ceramic tiles industries, which experienced similar forms of defects.     

多特征融合的瓷砖表面缺陷检测算法研究

鉴于单一特征在瓷砖种类较多的情况下,存在对瓷砖表面缺陷内容表达不明显,导致复杂瓷砖识别率较低。针对这个问题,在词袋模型（BoF）框架的基础上,提出一种有效的多特征融合算法用于瓷砖缺陷检测。该算法采用改进后的SIFT和颜色矩融合特征作为瓷砖图像的区域特征描述;根据每种特征对瓷砖被分类的准确率大小,给提取到的两种区域特征分配各自的权重系数实现特征的加权融合;形成综合特征向量送入SVM分类器达到瓷砖缺陷分类的目的。通过不同类型的瓷砖样本进行实验表明,该算法识别率高,对复杂瓷砖能实现较好的分类。     

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.     

基于傅里叶变换的随机纹理瓷砖的高精度表面缺陷检测

针对经典缺陷检测算法不能很好地提取随机纹理瓷砖图像的缺陷的问题,提出一种基于傅里叶变换的随机纹理瓷砖表面缺陷高精度检测方法。在此基础上,完成了瓷砖表面缺陷检测硬件系统设计。对采集的瓷砖图像,首先利用傅里叶变换得到频率谱图像,然后研究截止频率参数对滤波的影响,设计最优化滤波器进行滤波,再通过傅里叶逆变换获得重构图像,达到抑制背景纹理信息,加强缺陷区域信息的目的,最后通过阈值化和形态学操作获得缺陷区域。实验结果表明: 本方法对不同的随机纹理瓷砖样本进行缺陷检测的准确率高,在瓷砖缺陷检测中具有较高的实用价值。     

瓷砖图像的纹理特征分类研究

在已有的瓷砖图像分类系统中,仅靠颜色特征和简单的纹理边缘信息只能对无花纹的单色砖或简单花纹的瓷砖进行有效分类,对复杂图案的瓷砖存在识别率低的问题。针对此种情况,结合瓷砖图像的灰度共生矩阵和统计几何特征,将这些特征输入支持向量机进行特征分层分类。采用基于径向基核函数和[K]交叉验证法所得到的最优参数构造支持向量机,解决瓷砖纹理特征具有非线性的分类问题。用瓷砖生产线上采集的大量图像进行实验表明,该方法准确率高,分类效果好。     

基于PLC的瓷砖平整度在线检测系统研究

为实现瓷砖平整度的自动在线检测及分级,设计了基于PLC、组态软件和激光位移传感器的瓷砖平整度实时检测分级系统。系统由传送、检测和分级三部分组成。该检测系统采用光学三角法检测技术,通过编码器及PLC的高速计数器功能对移动中的待检测瓷砖的采样位置进行精确定位,使用激光位移传感器对瓷砖表面进行信息采集,经AD转换后在PLC内部按照特定的算法进行平整度运算,以PLC为核心实现瓷砖的分级处理和对设备的整体控制。实验表明该检测系统高效、稳定、可靠。瓷砖平整度检测精度为±0.1 mm,多次同方向检测精度为±0.05 mm,检测速度为每分钟40片,检测准确度可达到95%以上,适用于当前瓷砖生产过程的质量控制。     

基于边界特征配准的墙地砖缺陷检测研究

该文结合radon变换和几何推理,研究了基于墙地砖边界的用于规则图案表面缺陷检测的图像配准方法。实验证明该算法简单快捷,能检测出墙地砖的一般常见缺陷。     

Control of a ceramic tiles cooling process based on water spraying

The control of the surface temperature of ceramic tiles in a real industrial production line is developed. The process consists of a transportation band that carries the hot tiles through a water sprayer whose objective is to reduce its temperature. Two input signals can be modified: the velocity of the transportation band and the flow rate of the sprayer. In order to control the outlet surface temperature, the quantity of water deposited (and hence evaporated) per tile, that is a static function of the velocity and the flow rate, is used as the control input. The inlet temperature has a tile to tile fast pattern variation and a slow average change. First, the experimental identification of the process model is carried out. Then a feedback PI controller based on the measurement of the outlet temperature is then tested, showing a good average tracking, but a poor compensation of the fast variations. An adaptive feedforward control based on the measurement of the inlet and outlet temperatures is developed and also tested in the plant, showing a much better performance, but a higher cost. Finally, a disturbance observer based feedforward control is tested, showing an intermediate performance and cost.     

Activatable tiles for compact robust programmable molecular assembly and other applications

Algorithmic DNA self-assembly is capable of forming complex patterns and shapes, that have been shown theoretically, and experimentally. Its experimental demonstrations, although improving over recent years, have been limited by significant assembly errors. Since 2003 there have been several designs of error-resilient tile sets but all of these existing error-resilient tile systems assumed directional growth of the tiling assembly. This is a very strong assumption because experiments show that tile self-assembly does not necessarily behave in such a fashion, since they may also grow in the reverse of the intended direction. The assumption of directional growth of the tiling assembly also underlies the growth model in theoretical assembly models such as the TAM. What is needed is a means for enforce this directionality constraint, which will allow us to reduce assembly errors. In this paper we describe a protection/deprotection strategy to strictly enforce the direction of tiling assembly growth so that the assembly process is robust against errors. Initially, we start with (1) a single “activated” tile with output pads that can bind with other tiles, along with (2) a set of “deactivated” tiles, meaning that the tile’s output pads are protected and cannot bind with other tiles. After other tiles bind to a “deactivated” tile’s input pads, the tile transitions to an active state and its output pads are exposed, allowing further growth. When these are activated in a desired order, we can enforce a directional assembly at the same scale as the original one. Such a system can be built with minimal modifications of existing DNA tile nanostructures. We propose a new type of tiles called activatable tiles and its role in compact proofreading. Activatable tiles can be thought of as a particular case of the more recent signal tile assembly model, where signals transmit binding/unbinding instructions across tiles on binding to one or more input sites. We describe abstract and kinetic models of activatable tile assembly and show that the error rate can be decreased significantly with respect to Winfree’s original kinetic tile assembly model without considerable decrease in assembly growth speed. We prove that an activatable tile set is an instance of a compact, error-resilient and self-healing tile-set. We describe a DNA design of activatable tiles and a mechanism of deprotection using DNA polymerization and strand displacement. We also perform detailed stepwise simulations using a DNA Tile simulator Xgrow, and show that the activatable tiles mechanism can reduce error rates in self assembly. We conclude with a brief discussion on some applications of activatable tiles beyond computational tiling, both as (1) a novel system for concentration of molecules, and (2) a catalyst in sequentially triggered chemical reactions.     

一种改进DCGANs网络的磁瓦缺陷图像生成方法研究

基于机器视觉的磁瓦表面缺陷检测研究对于改进磁瓦生产工艺、提升磁瓦生产效率有着重要意义.但在研究过程中,存在磁瓦含缺陷样本收集困难、不同缺陷样本数不均匀、缺陷类型单一等问题.本文提出一种使用高斯混合模型的深度卷积生成对抗网络(Gaussian Mixture Model Deep Convolution Generative Adversarial Networks,GMM-DCGANs)生成含缺陷磁瓦图像的方法.在深度卷积生成对抗网络的基础上,将生成图像的输入噪声潜在空间复杂化为高斯混合模型,从而提高图像生成网络对有限数量且具有类间及类内多样性训练样本的学习能力.实验结果表明,GMMDCGANs网络可以生成质量更好、缺陷类型更加丰富的磁瓦缺陷图像,并且生成的图像满足缺陷检测及分类的要求.     

基于图像的异型墙地砖在线分道系统

提出了一种异型墙地砖在线提取和纹理比较的方法。将CCD采集的墙地砖图像进行灰度阈值分割后,经过以矩形模式为特征的轮廓搜索,对原始图像中的砖面区域做标准化仿射变换处理,实现墙地砖的在线提取。依据计算共生矩阵特征向量,采用最小距离分类原理进行纹理比较分类决策,并采用自适应阈值参数加强算法的鲁棒性。基于所提取算法研制了异型墙地砖在线分道系统,并在实际现场运行成功,取得良好的分道效果。     

基于共生矩阵和颜色特征的墙地砖缺陷自动检测的研究

该文提出了一种用于墙地砖自动缺陷检测的新算法,该算法综合了颜色的空间分布信息和比例分布信息,应用共生矩阵纹理特征与颜色统计特征构造一个判断矢量,能对复杂纹理的多色墙地砖进行各种缺陷检测,实验证明该算法是有效的。     

基于小波变换的图像纹理特征提取方法及其应用

针对瓷砖表面色差的在线检测问题,提出了一种基于小波变换的图像纹理特征提取方法.瓷砖图像经过预处理后,对图像各通道进行二层小波分解并提取各细节子图的能量特征.该能量信号融合了颜色和纹理的信息,将其作为区分不同色号瓷砖的特征量,并由最小距离分类器进行分类决策.实验结果表明,对比已有的研究中多采用的颜色直方图分布法,该方法能更好地反映颜色的空间分布信息,满足用户需求.     

The effect of malformed tiles on tile assemblies within the kinetic tile assembly model

Many different constructions of proofreading tile sets have been proposed in the literature to reduce the effect of deviations from ideal behaviour of the dynamics of the molecular tile self-assembly process. In this paper, we consider the effect on the tile assembly process of a different kind of non-ideality, namely, imperfections in the tiles themselves. We assume a scenario in which some small proportion of the tiles in a tile set are “malformed”. We study, through simulations, the effect of such malformed tiles on the self-assembly process within the kinetic Tile Assembly Model (kTAM). Our simulation results show that some tile set constructions show greater error-resilience in the presence of malformed tiles than others. For example, the 2- and 3-way overlay compact proofreading tile sets of Reif et al. (DNA Computing 10, Lecture Notes in Computer Science, vol 3384. Springer, 2005) are able to handle malformed tiles quite well. On the other hand, the snaked proofreading tile set of Chen and Goel (DNA Computing 10, Lecture Notes in Computer Science, vol 3384. Springer, 2005) fails to form even moderately sized tile assemblies when malformed tiles are present. We show how the Chen–Goel construction may be modified to yield new snaked proofreading tile sets that are resilient not only to errors intrinsic to the assembly process, but also to errors caused by malformed tiles.     

Hierarchical self assembly of patterns from the Robinson tilings: DNA tile design in an enhanced Tile Assembly Model

We introduce a hierarchical self assembly algorithm that produces the quasiperiodic patterns found in the Robinson tilings and suggest a practical implementation of this algorithm using DNA origami tiles. We modify the abstract Tile Assembly Model (aTAM), to include active signaling and glue activation in response to signals to coordinate the hierarchical assembly of Robinson patterns of arbitrary size from a small set of tiles according to the tile substitution algorithm that generates them. Enabling coordinated hierarchical assembly in the aTAM makes possible the efficient encoding of the recursive process of tile substitution.     

基于机器视觉的随机纹理瓷砖的分选系统

针对日益加快的瓷砖生产速度与缓慢的人工分选速度之间不协调导致的瓷砖出产效率低下的问题,提出了以机器视觉软件HALCON 11.0为软件开发平台的结合瓷砖颜色、纹理特征提取的算法,以及针对多分类问题的改进多层感知器神经网络算法(MLPNN).首先对拍摄到的瓷砖图像进行去噪预处理,在HSI颜色空间中提取瓷砖的色调(Hue)特征并计算反映瓷砖的纹理特征的灰度共生矩阵(GLCM)和灰度幅值分布特征,再将得到的特征作为多层感知器的神经网络输入层神经元,然后设计以softmax为激活函数的多层感知器神经网络来进行模式匹配,并与BP神经网络模式匹配方法进行对比,最终搭建出具有简单人机交互界面的随机纹理瓷砖的分选实验样机.实验结果表明:本系统对实验的各类随机纹理瓷砖的分选准确率都在90%以上,具有较高的分选准确率,能应用于瓷砖生产实践.     

基于多尺度卷积神经网络和类内mixup操作的磁瓦表面质量识别

铁氧体磁瓦由于形状的不规则性和表面缺陷的多样性给基于计算机视觉的表面质量识别带来很大的挑战。针对该问题,将深度学习技术引入到磁瓦表面质量识别中,提出一种基于卷积神经网络的磁瓦表面质量识别系统。首先将磁瓦目标从采集到的图像中分割出来并进行旋转从而得到标准图像,然后把改进后的多尺度ResNet18作为骨干网络来设计识别系统。训练时,设计一种新颖的类内mixup操作来提高系统对样本的泛化能力。为了更加贴近实际应用场景,在考虑到光线变化、姿态差异等因素的前提下构建了磁瓦缺陷数据集。在自建的数据集中进行实验的结果表明,该系统可以达到97.9%的识别准确率,为磁瓦缺陷的自动识别提供了可行的思路。     

基于矢量瓦片的点状要素注记处理技术

矢量瓦片体积小,可高度压缩,受网络带宽开销和存储空间的限制较小。地图瓦片化对桌面软件点注记处理带来挑战,不仅是点注记的处理存在重要注记被次要注记压盖、同级注记之间互相压盖、注记与要素压盖等问题,同时瓦片化也带来了注记被瓦片边缘截断显示不完全的问题,这些问题严重影响了地图的可读性和信息传递功能。本文针对以上问题总结了矢量瓦片点注记处理原则,通过设计矢量瓦片的组织结构,确定注记搭配表的JSON组织形式,明确矢量瓦片点注记的绘制流程,根据矢量瓦片特点使用四叉编码进行目标过滤,使用R树作为高效空间索引,并采用基于注记优先级的避障技术解决上述点注记处理带来的问题。     

基于虚拟仪器的瓷砖平整度自动检测系统

为实现瓷砖表面平整度误差的自动检测和产品质量的自动分级，探讨了瓷砖表面平整度检测的原理和方法。将虚拟仪器技术应用于瓷砖表面平整度的自动检测研究，以非接触式光纤位移传感器、数据采集卡、PC机作为硬件配置，以LabVIEW作为软件开发平台，设计了瓷砖表面平整度自动检测系统：实际应用表明，该系统可以自动检测瓷砖表面平整度，并对产品进行分级，适合于实际生产过程的质量控制.     

Optimal tiling of heterogeneous images

A novel information theoretical approach has been developed, implemented and tested to approximate large, heterogeneous images with maps of varying spatial resolution and predefinedcomplexity. The goal of the approximation is the derivation of units in the spatial domain rather than determining classes in the attribute (spectral) domain. The proposed procedure is a regular, hierarchical tiling. The value of each tile is the local mean and the parti tion leads to a map represented by a region quadtree with minimum Kullback-divergence from the original image. Kullback-divergence is a non-parametric measure of dissimilarity of two spatial distributions and is applied here because of several advantageous properties. This tiling procedure can be also viewed as data compression, and it optimizes information loss under constraint on the spatial arrangement and number of tiles. The methodology is illustrated by the sampling design of an environmental soil mapping project of the salt-affected rangeland in Hortobagy, north-east Hungary.