Improving the industrial classification of cork stoppers by using image processing and Neuro-Fuzzy computing

This paper presents a solution to a problem existing in the cork industry: cork stopper/disk classification according to their quality using a visual inspection system. Cork is a natural and heterogeneous (remarkable variability among different samples, being impossible to find two samples with the same morphological distribution in its defects) material; therefore, its automatic classification (seven quality classes exist) is very difficult. The solution proposed in this paper evaluates the following procedures: quality discriminatory features extraction and classifiers analysis. Each procedure focused on the study of aspects that could influence cork quality. Experiments show that the best results are obtained by system specific features: cork area occupied by defects (after thresholding), size of the biggest defect within the cork area (morphological operations), and the Laws TEMs E5L5TR, E5E5TR, S5S5TR, W5W5TR, all working on a Neuro-Fuzzy classifier. In conclusion, the results of this study represent an important contribution to improve quality control in the cork industry.     

Stochastic differential games and inverse optimal control and stopper policies

In this paper, we consider a two-player stochastic differential game problem over an infinite time horizon where the players invoke controller and stopper strategies on a nonlinear stochastic differential game problem driven by Brownian motion. The optimal strategies for the two players are given explicitly by exploiting connections between stochastic Lyapunov stability theory and stochastic Hamilton–Jacobi–Isaacs theory. In particular, we show that asymptotic stability in probability of the differential game problem is guaranteed by means of a Lyapunov function which can clearly be seen to be the solution to the steady-state form of the stochastic Hamilton–Jacobi–Isaacs equation, and hence, guaranteeing both stochastic stability and optimality of the closed-loop control and stopper policies. In addition, we develop optimal feedback controller and stopper policies for affine nonlinear systems using an inverse optimality framework tailored to the stochastic differential game problem. These results are then used to provide extensions of the linear feedback controller and stopper policies obtained in the literature to nonlinear feedback controllers and stoppers that minimise and maximise general polynomial and multilinear performance criteria.     

Subjective measurement of cosmetic defects using a Computational Intelligence approach

This paper presents a Computational Intelligence scheme to deal with subjective human inspection tasks in the industry that are subjective measurements. The scheme is used to solve two cosmetic subjective measurements tasks, classification of cosmetic defects and detection of non-uniform color regions in a translucent film. The first problem is solved with two approaches supervised and unsupervised Artificial Neural Networks. Both techniques yield the same performance, 92.35% of correct classification. Considering that a human inspector has a performance between 85% and 90%, the performance achieved is acceptable. The second problem is faced with a hybrid system based on fuzzy clustering and a Self-Organizing Map. The hybrid approach involves management of uncertainty through fuzzy theory and unsupervised training supported by the SOM. The proposed system is able to find non-uniform color regions with better resolution than a human inspector. The system also showed to be more sensitive than a simple fuzzy clustering approach.     

Automated defect inspection system for metal surfaces based on deep learning and data augmentation

Recent efforts to create a smart factory have inspired research that analyzes process data collected from Internet of Things (IOT) sensors, to predict product quality in real time. This requires an automatic defect inspection system that quantifies product quality data by detecting and classifying defects in real time. In this study, we propose a vision-based defect inspection system to inspect metal surface defects. In recent years, deep convolutional neural networks (DCNNs) have been used in many manufacturing industries and have demonstrated the excellent performance as a defect classification method. A sufficient amount of training data must be acquired, to ensure high performance using a DCNN. However, owing to the nature of the metal manufacturing industry, it is difficult to obtain enough data because some defects occur rarely. Owing to this imbalanced data problem, the generalization performance of the DCNN-based classification algorithm is lowered. In this study, we propose a new convolutional variational autoencoder (CVAE) and deep CNN-based defect classification algorithm to solve this problem. The CVAE-based data generation technology generates sufficient defect data to train the classification model. A conditional CVAE (CCVAE) is proposed to generate images for each defect type in a single CVAE model. We also propose a classifier based on a DCNN with high generalization performance using data generated from the CCVAE. In order to verify the performance of the proposed method, we performed experiments using defect images obtained from an actual metal production line. The results showed that the proposed method exhibited an excellent performance.     

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.     

Rule extraction from artificial neural networks to discover causes of quality defects in fabric production

In this paper, a novel classification rule extraction algorithm which has been recently proposed by authors is employed to determine the causes of quality defects in a fabric production facility in terms of predetermined parameters like machine type, warp type etc. The proposed rule extraction algorithm works on the trained artificial neural networks in order to discover the hidden information which is available in the form of connection weights in them. The proposed algorithm is mainly based on a swarm intelligence metaheuristic which is known as Touring Ant Colony Optimization (TACO). The algorithm has a hierarchical structure with two levels. In the first level, a multilayer perceptron type neural network is trained and its weights are extracted. After obtaining the weights, in the second level, the TACO-based algorithm is applied to extract classification rules. The main purpose of the present work is to determine and analyze the most effective parameters on the quality defects in fabric production. The parameters and their levels which give the best quality results are tried to be discovered and evaluated by making use of the proposed algorithm. It is also aimed to compare the accuracy of proposed algorithm with several other rule-based algorithms in order to present its competitiveness.     

Towards true linguistic modelling through optimal numerical solutions

This paper is concerned with both the problems of quantitative and qualitative modelling of complex systems by using fuzzy techniques. A unified approach for the identification and subsequent extraction of linguistic knowledge of systems using fuzzy relational models is addressed. This approach deals with the identification problem by means of optimal numerical solutions based on weighted least squares and quadratic programming formulations. The linguistic knowledge is extracted in the form of consistent fuzzy rules that describe linguistically the behaviour of the identified system. A new methodology for the simplification of the extracted rules is derived by using a pruning criterion based on the representability matrix concept introduced in previous work. Several numerical aspects concerning the proposed optimization schemes and a covering discussion about the linguistic interpretation of the resulting models are also included together with illustrative examples in the contexts of pattern classification and dynamic systems identification. The paper also provides an overview of fuzzy modelling techniques that intends to situate the relational models among other fuzzy model architectures typically adopted in the literature, highlighting their main advantages and drawbacks.     

Feature extraction based on decision boundaries

A novel approach to feature extraction for classification based directly on the decision boundaries is proposed. It is shown how discriminantly redundant features and discriminantly informative features are related to decision boundaries. A procedure to extract discriminantly informative features based on a decision boundary is proposed. The proposed feature extraction algorithm has several desirable properties: (1) it predicts the minimum number of features necessary to achieve the same classification accuracy as in the original space for a given pattern recognition problem; and (2) it finds the necessary feature vectors. The proposed algorithm does not deteriorate under the circumstances of equal class means or equal class covariances as some previous algorithms do. Experiments show that the performance of the proposed algorithm compares favorably with those of previous algorithms     

基于深度学习的织物缺陷在线检测算法

织物缺陷在线检测是纺织行业面临的重大难题，针对当前织物缺陷检测中存在的误检率高、漏检率高、实时性不强等问题，提出了一种基于深度学习的织物缺陷在线检测算法。首先基于GoogLeNet网络架构，并参考其他分类模型的经典算法，搭建出适用于实际生产环境的织物缺陷分类模型；其次利用质检人员标注的不同种类织物图片组建织物缺陷数据库，并用该数据库对织物缺陷分类模型进行训练；最后对高清相机在织物验布机上采集的图片进行分割，并将分割后的小图以批量的方式传入训练好的分类模型，实现对每张小图的分类，以此来检测缺陷并确定其位置。对该模型在织物缺陷数据库上进行了验证。实验结果表明：织物缺陷分类模型平均每张小图的测试时间为0.37 ms，平均测试时间比GoogLeNet减少了67%，比ResNet-50减少了93%；同时模型在测试集上的正确率达到99.99%。说明其准确率与实时性均满足实际工业需求。     

Power quality time series data mining using S-transform and fuzzy expert system

This paper presents a new approach for power quality time series data mining using S-transform based fuzzy expert system (FES). Initially the power signal time series disturbance data are pre-processed through an advanced signal processing tool such as S-transform and various statistical features are extracted, which are used as inputs to the fuzzy expert system for power quality event detection. The proposed expert system uses a data mining approach for assigning a certainty factor for each classification rule, thereby providing robustness to the rule in the presence of noise. Further to provide a very high degree of accuracy in pattern classification, both the Gaussian and trapezoidal membership functions of the concerned fuzzy sets are optimized using a fuzzy logic based adaptive particle swarm optimization (PSO) technique. The proposed hybrid PSO-fuzzy expert system (PSOFES) provides accurate classification rates even under noisy conditions compared to the existing techniques, which show the efficacy and robustness of the proposed algorithm for power quality time series data mining.     

Asymmetric Principal Component and Discriminant Analyses for Pattern Classification

This paper studies the roles of the principal component and discriminant analyses in the pattern classification and explores their problems with the asymmetric classes and/or the unbalanced training data. An asymmetric principal component analysis (APCA) is proposed to remove the unreliable dimensions more effectively than the conventional PCA. Targeted at the two-class problem, an asymmetric discriminant analysis in the APCA subspace is proposed to regularize the eigenvalue that is, in general, a biased estimate of the variance in the corresponding dimension. These efforts facilitate a reliable and discriminative feature extraction for the asymmetric classes and/or the unbalanced training data. The proposed approach is validated in the experiments by comparing it with the related methods. It consistently achieves the highest classification accuracy among all tested methods in the experiments.     

A demerit-fuzzy rating system,monitoring scheme and classification for manufacturing processes

For monitoring online manufacturing processes, the proportion of weights imposed on each type of product’s defects (nonconformities or demerits) has a profoundly effective impact on control charts’ performance. Apparently, the demerit-chart approach is superior than the widely-used c-chart scheme, because it allows us to place relative precise weights (real numbers) on defects according to their distinctly inferior degrees affecting the product quality so that the abnormal variations of processes can be literally exposed. However, in many applications, the seriousness of defects is evaluated partially or entirely by the inspectors’ perceptive judgement or knowledge, so with the precise-weight assignment, the demerit rating mechanism is considered to be somewhat constrained and subjective which inevitably leads to the targeted manufacturing process with limited and possibly biased information for online surveillance. To cope with the drawback, a demerit-fuzzy rating system and monitoring scheme is proposed in this paper. We first incorporate fuzzy weights (fuzzy numbers) to properly reflect the severity measures of defects which are categorized linguistically. Then, based on properties of fuzzy set theory and proposed approaches for fuzzy-number ranking, we develop the demerit-fuzzy charting scheme which is capable of discriminating process conditions into multi-intermittent statuses between in-control and out-of-control. This approach improves the traditional process control techniques with the binary-classification restraint for the process conditions. Finally, the proposed demerit-fuzzy rating system, monitoring scheme, and classification is elucidated by an application in garment industry to monitor textile-stitching nonconformities conditions.     

基于级联卷积神经网络的复杂花色布匹瑕疵检测算法

当布匹的背景信息复杂多变时,复杂花色布匹的瑕疵定位与分类较为困难.针对这一问题,文中提出基于级联卷积神经网络的复杂花色布匹瑕疵检测算法.首先,使用双路残差的骨干特征提取网络,在缺陷图和模板图上提取并融合特征.然后,设计密度聚类边框生产器,指导框架中区域候选网络的预检测框设计.最后,通过级联回归方法完成瑕疵的精确定位和分类.采用工业现场采集的布匹图像数据进行训练与预测,结果表明,文中算法的精准率和召回率较高.     

A neural network approach for defect identification and classification on leather fabric

In this paper, an automated vision system is presented to detect and classify surface defects on leather fabric. Visual defects in a gray-level image are located through thresholding and morphological processing, and their geometric information is immediately reported. Three input feature sets are proposed and tested to find the best set to characterize five types of defects: lines, holes, stains, wears, and knots. Two multilayered perceptron models with one and two hidden layers are tested for the classification of defects. If multiple line defects are identified on a given image as a result of classification, a line combination test is conducted to check if they are parts of larger line defects. Experimental results on 140 defect samples show that two-layered perceptrons are better than three-layered perceptrons for this problem. The classification results of this neural network approach are compared with those of a decision tree approach. The comparison shows that the neural network classifier provides better classification accuracy despite longer training times.     

An efficient discriminant-based solution for small sample size problem

Classification of high-dimensional statistical data is usually not amenable to standard pattern recognition techniques because of an underlying small sample size problem. To address the problem of high-dimensional data classification in the face of a limited number of samples, a novel principal component analysis (PCA) based feature extraction/classification scheme is proposed. The proposed method yields a piecewise linear feature subspace and is particularly well-suited to difficult recognition problems where achievable classification rates are intrinsically low. Such problems are often encountered in cases where classes are highly overlapped, or in cases where a prominent curvature in data renders a projection onto a single linear subspace inadequate. The proposed feature extraction/classification method uses class-dependent PCA in conjunction with linear discriminant feature extraction and performs well on a variety of real-world datasets, ranging from digit recognition to classification of high-dimensional bioinformatics and brain imaging data.     

一种新的特征提取方法及其在模式识别中的应用

核典型相关分析(KCCA)是一种有监督的机器学习方法,可以有效地提取非线性特征。然而随着训练样本数目的增加,标准的KCCA方法的计算复杂度会随之增加。针对此缺点,提出一种改进的KCCA方法：首先用几何特征选择方法选择一个训练样本子集并将其映射到再生核希尔伯特空间(RKHS),然后设计了一种提升特征提取效率的算法,该算法按照对特征分类贡献的大小巧妙地选取样本的特征值,进而求出其相应的特征向量,最后将改进的KCCA与支持向量数据描述(SVDD)多分类器相结合用于分类识别。在ORL人脸图像数据库上的实验结果表明,改进的方法相对传统的KCCA方法,在不影响识别率的情况下提高了人脸识别速度,减小了系统存储量。     

Finger-vein pattern identification using principal component analysis and the neural network technique

This paper presents a personal identification system using finger-vein patterns with component analysis and neural network technology. In the proposed system, the finger-vein patterns are captured by a device that can transmit near infrared through the finger and record the patterns for signal analysis. The proposed biometric system for verification consists of a combination of feature extraction using principal component analysis (PCA) and pattern classification using back-propagation (BP) network and adaptive neuro-fuzzy inference system (ANFIS). Finger-vein features are first extracted by PCA method to reduce the computational burden and removes noise residing in the discarded dimensions. The features are then used in pattern classification and identification. To verify the effect of the proposed ANFIS in the pattern classification, the BP network is compared with the proposed system. The experimental results indicated the proposed system using ANFIS has better performance than the BP network for personal identification using the finger-vein patterns.     

Finger-vein pattern identification using SVM and neural network technique

This paper presents a support vector machine (SVM) technique for finger-vein pattern identification in a personal identification system. Finger-vein pattern identification is one of the most secure and convenient techniques for personal identification. In the proposed system, the finger-vein pattern is captured by infrared LED and a CCD camera because the vein pattern is not easily observed in visible light. The proposed verification system consists of image pre-processing and pattern classification. In the work, principal component analysis (PCA) and linear discriminant analysis (LDA) are applied to the image pre-processing as dimension reduction and feature extraction. For pattern classification, this system used an SVM and adaptive neuro-fuzzy inference system (ANFIS). The PCA method is used to remove noise residing in the discarded dimensions and retain the main feature by LDA. The features are then used in pattern classification and identification. The accuracy of classification using SVM is 98% and only takes 0.015 s. The result shows a superior performance to the artificial neural network of ANFIS in the proposed system.     

An automated industrial conveyor belt system using image processing and hierarchical clustering for classifying marble slabs

Although there are many industrial machines used in marble industry, classification of marble slabs in terms of quality is generally performed by human experts. Due to economic losses of this rather subjective process, automatic and computerized methods are needed in order to obtain reproducible and objective results in classification. With the aim of remedying this insufficiency in marble industry, a new electro-mechanical system, which automatically classifies marble slabs while they are on a conveyor belt and groups them with the help of a control mechanism, is proposed. The developed system is composed of two parts: the software part acquires digital images of marble slabs, extracts several features using these images, and finally performs the classification using clustering methods. The hardware part is composed of a conveyor belt, a serial port communication system, pneumatic pistons, a programmable logic controller (PLC), and its control circuits, all employed together for grouping the marble slabs mechanically. Although similar studies exist, this paper proposes three novelties over the existing systems. Firstly, a new hierarchical clustering approach is introduced for quality classification without requiring a training set. Secondly, a new feature set based on morphological properties of marble surface images is proposed. Finally, an electro-mechanical system is designed for accomplishing the task of sorting out the classified marble slabs. In the literature, only a system with a labeling mechanism has been presented. Our system, on the other hand, comes with a complete conveyor belt acting as an element that links the production line with the proposed system. This allows the possibility of embedding the proposed system into the production line of a marble factory. It has been observed that although the performance of the developed system is not as high as neural network based systems that use training, it could still be employed in industry when there is no available training set of samples. With this advantage, it provides an increase in the quality control standards of marble slab classification, since marbles are classified with an objective and uniform-through-time criterion.     

基于改进ShuffleNetV2的轻量级花色布匹瑕疵检测

布匹瑕疵检测是纺织业质量管理的重要环节.在嵌入式设备上实现准确、快速的布匹瑕疵检测能有效降低成本,因而价值巨大.考虑到实际生产中花色布匹瑕疵具有背景复杂、数量差异大、极端长宽比和小瑕疵占比高等结构特性,提出一种基于轻量级模型的花色布匹瑕疵检测方法并将其部署在嵌入式设备Raspberry Pi 4B上.首先在一阶段目标检测网络YOLO的基础上用轻量级特征提取网络ShuffleNetV2提取花色布匹瑕疵的特征,以减少网络结构复杂度及参数量,提升检测速度;其次是检测头的解耦合,将分类与定位任务分离,以提升模型收敛速度;此外引入CIoU作为瑕疵位置回归损失函数,提高瑕疵定位准确性.实验结果表明,本文算法在Raspberry Pi 4B上可达8.6 FPS的检测速度,可满足纺织工业应用需求.