Search

One of the primary applications of machine vision is automating the visual inspection of industrial products. Significant advancements have been made in the development of the technology. However, the inspection for certain difficult-todetect defects (such as shallow concave defects on glossy surfaces) has not yet been automated. However, visual inspectors know from experience that slight irregularities are easier to perceive when the viewpoint is held just above the surface. This study analyzes the effect of this "just above the surface view" on the visualization of defects through optical simulation analysis. Additionally, it clarifies that a lower viewpoint is not always optimal, depending on the degree of inclination of the defect surface. The new findings presented in this paper can contribute to the optimal design of the optical system of a visual inspection system. [ABSTRACT FROM AUTHOR]

In this study, a two-stage attention-based variational long short-term memory (LSTM) that allows fault detection and diagnosis in electrolytic copper manufacturing processes is proposed. As the surface quality of electrolytic copper determines the yield and quality of the product, an automated surface inspection (ASI) system has been introduced at various electrolytic copper production sites. Using the ASI system, the number of bumps on the electrolytic copper surface was converted into numerical data and the product was graded based on the data. However, when ASI is performed, it is difficult to accurately identify the variables that cause low-grade electrolytic copper. This is the first study to utilize feature data from an ASI system for fault detection and diagnosis in an electrolytic copper manufacturing process. Using a two-stage attention structure, important input and temporal features were extracted even though the noise ratio was high. In addition, the generalization performance was improved using a drop connect and variational LSTM, which can solve the overfitting problem. Experimental results using real-world data from the copper production process showed that the proposed model outperformed other time-series classification models. In addition, the proposed method was proven successful in fault diagnosis using attention weights. [ABSTRACT FROM AUTHOR]

Automated surface inspection (ASI) is critical to quality control in industrial manufacturing processes. Recent advances in deep learning have produced new ASI methods that automatically learn high-level features from training samples while being robust to changes and capable of detecting different types of surfaces and defects. However, they usually rely heavily on manpower to collect and label training samples. In this paper, a generic semi-supervised deep learning-based approach for ASI that requires a small quantity of labeled training data is proposed. While the approach follows the MixMatch rules to conduct sophisticated data augmentation, we introduce a new loss function calculation method and propose a new convolutional neural network based on a residual structure to achieve accurate defect detection. An experiment on two public datasets (DAGM and NEU) and one industrial dataset (CCL) is carried out. For public datasets, the experimental results are compared against several best benchmarks in the literature. For the industrial dataset, the results are compared against deep learning methods based on benchmark neural networks. The proposed method achieves the best performance in all comparisons. In addition, a comparative experiment of model performance given a different number of labeled samples is conducted, demonstrating that the proposed method can achieve good performance with few labeled training samples.

With the advancement of industrial intelligence, defect recognition has become an indispensable part of facilitating surface quality in the steel manufacturing process. To assure product quality, most previous studies were typically trained with many defect samples. Nonetheless, a large quantity of defect samples is difficult to obtain, owing to the rare occurrence of defects. In general, deep learning-based methods underperformed as they have inherent limitations due to inadequate information, thereby restraining the application of models. In this study, a two-level Gaussian pyramid is applied to decompose raw data into different resolution levels simultaneously filtering the noises to acquire compact and representative features. Subsequently, a multi-receptive field fusion-based network (MRFFN) is developed to learn the hierarchical features and synthesize the respective prediction scores to form the final recognition result. As a result, the proposed method is capable of exhibiting an outstanding performance of 99.75% when trained using a lightweight dataset. In addition, the experiments conducted using the disturbance defect dataset showed the robustness of the proposed MRFFN against common noises and motion blur. [ABSTRACT FROM AUTHOR]

Manual surface inspection methods performed by quality inspectors do not satisfy the continuously increasing quality standards of industrial manufacturing processes. Machine vision provides a solution by using an automated visual inspection (AVI) system to perform quality inspection and remove defective products. Numerous studies and works have been conducted on surface inspection algorithms. With the advent of deep learning, a number of new algorithms have been developed for better inspection. In this paper, the state-of-the-art in surface defect inspection using deep learning is presented. In particular, we focus on the inspection of industrial products in semiconductor, steel, and fabric manufacturing processes. This work makes three contributions. First, we present the prior literature reviews on vision-based surface defect inspection and analyze the recent AVI-related hardware and software. Second, we review traditional surface defect inspection algorithms including statistical methods, spectral methods, model-based methods, and learning-based methods. Third, we investigate recent advances in deep learning-based inspection algorithms and present their applications in the steel, fabric, and semiconductor industries. Furthermore, we provide information on publicly available datasets containing surface image samples to facilitate the research on deep learning-based surface inspection. [ABSTRACT FROM AUTHOR]

With the advancement of industrial intelligence, defect recognition has become an indispensable part of facilitating surface quality in the steel manufacturing process. To assure product quality, most previous studies were typically trained with many defect samples. Nonetheless, a large quantity of defect samples is difficult to obtain, owing to the rare occurrence of defects. In general, deep learning-based methods underperformed as they have inherent limitations due to inadequate information, thereby restraining the application of models. In this study, a two-level Gaussian pyramid is applied to decompose raw data into different resolution levels simultaneously filtering the noises to acquire compact and representative features. Subsequently, a multi-receptive field fusion-based network (MRFFN) is developed to learn the hierarchical features and synthesize the respective prediction scores to form the final recognition result. As a result, the proposed method is capable of exhibiting an outstanding performance of 99.75% when trained using a lightweight dataset. In addition, the experiments conducted using the disturbance defect dataset showed the robustness of the proposed MRFFN against common noises and motion blur.

Aiming at the problems of complex texture, variable interference factors and large sample acquisition in surface defect detection, a generic method of automated surface defect detection based on a bilinear model was proposed. To realize the automatic classification and localization of surface defects, a new Double-Visual Geometry Group16 (D-VGG16) is firstly designed as feature functions of the bilinear model. The global and local features fully extracted from the bilinear model by D-VGG16 are output to the soft-max function to realize the automatic classification of surface defects. Then the heat map of the original image is obtained by applying Gradient-weighted Class Activation Mapping (Grad-CAM) to the output features of D-VGG16. Finally, the defects in the original input image can be located automatically after processing the heat map with a threshold segmentation method. The training process of the proposed method is characterized by a small sample, end-to-end, and is weakly-supervised. Furthermore, experiments are performed on two public and two industrial datasets, which have different defective features in texture, shape and color. The results show that the proposed method can simultaneously realize the classification and localization of defects with different defective features. The average precision of the proposed method is above 99% on the four datasets, and is higher than the known latest algorithms. [ABSTRACT FROM AUTHOR]

Copyright of Technisches Messen is the property of De Gruyter and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aiming at the problems of complex texture, variable interference factors and large sample acquisition in surface defect detection, a generic method of automated surface defect detection based on a bilinear model was proposed. To realize the automatic classification and localization of surface defects, a new Double-Visual Geometry Group16 (D-VGG16) is firstly designed as feature functions of the bilinear model. The global and local features fully extracted from the bilinear model by D-VGG16 are output to the soft-max function to realize the automatic classification of surface defects. Then the heat map of the original image is obtained by applying Gradient-weighted Class Activation Mapping (Grad-CAM) to the output features of D-VGG16. Finally, the defects in the original input image can be located automatically after processing the heat map with a threshold segmentation method. The training process of the proposed method is characterized by a small sample, end-to-end, and is weakly-supervised. Furthermore, experiments are performed on two public and two industrial datasets, which have different defective features in texture, shape and color. The results show that the proposed method can simultaneously realize the classification and localization of defects with different defective features. The average precision of the proposed method is above 99% on the four datasets, and is higher than the known latest algorithms.

Copyright of Technisches Messen is the property of De Gruyter and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

• A novel Category-aware Conv-Pooling module is proposed, which explores weak image tag annotation to extract spatial information. • Knowledge distillation strategy is adopted to force the feature of a student CADN to mimic that of a teacher CADN, leading to accuracy improvement. • As verified, weakly supervised defect detection is achieved and competitive results are obtained by using the proposed CADN method. • In CADN, human labeling effort, accuracy and speed are simultaneously considered, making the method practical in industrial applications. Large-scale data with human annotations is of crucial importance for training deep convolutional neural network (DCNN) to ensure stable and reliable performance. However, accurate annotations, such as bounding box and pixel-level annotations, demand expensive labeling efforts, which has prevented wide application of DCNN in industries. Focusing on the problem of surface defect detection, this paper proposes a weakly supervised learning method named Category-Aware object Detection network (CADN) to tackle the dilemma. CADN is trained with image tag annotations only and performs image classification and defect localization simultaneously. The weakly supervised learning is achieved by extracting category-aware spatial information in a classification pipeline. CADN could be equipped with either a lighter or a larger backbone network as the feature extractor resulting in better real-time performance or higher accuracy. To address the two conflicting objectives simultaneously, both of which are significant concerns in industrial applications, knowledge distillation strategy is adopted to force the learned features of a lighter CADN to mimic that of a larger CADN. Accordingly, the accuracy of the lighter CADN is improved while high real-time performance is maintained. The proposed approach is verified on our own defect dataset as well as on an open-source defect dataset. As demonstrated, satisfied performance is achieved by the proposed method, which could meet industrial requirements completely. Meanwhile, the method minimizes human efforts involved in image labelling, thus promoting the applications of DCNN in industries. [ABSTRACT FROM AUTHOR]

Automated surface inspection has become a hot topic with the rapid development of machine vision technologies. Traditional machine vision methods need experts to carefully craft image features for defect detection. This limits their applications to wider areas. The emerging convolutional neural networks (CNN) can automatically extract features and yield good results in many cases. However, the CNN-based image classification methods are more suitable for flat surface texture inspection. It is difficult to accurately locate small defects in geometrically complex products. Furthermore, the computational power required in CNN algorithms is usually high and it is not efficient to be implemented on embedded hardware. To solve these problems, a smart surface inspection system is proposed using faster R-CNN algorithm in the cloud-edge computing environment. The faster R-CNN as a CNN-based object detection method can efficiently identify defects in complex product images and the cloud-edge computing framework can provide fast computation speed and evolving algorithm models. A real industrial case study is presented to illustrate the effectiveness of the proposed method. The results show that the proposed method can provide high detection accuracy within a short time. [ABSTRACT FROM AUTHOR]

Convolutional neural networks are becoming a popular tool for image processing in the engineering and manufacturing sectors. However, managing the storage and distribution of trained models is still a difficult task, partially due to the lack of standardized methods for deep neural network representation. Additionally, the interoperability between different machine learning frameworks remains poor. This paper seeks to address this issue by proposing a standardized format for convolutional neural networks, based on the Predictive Model Markup Language (PMML). A new standardized schema is proposed to represent a range of convolutional neural networks, including classification, regression and semantic segmentation systems. To demonstrate the practical application of this standard, a semantic segmentation model, which is trained to detect casting defects in Xray images, is represented in the proposed PMML format. A high-performance scoring engine is developed to evaluate images and videos against the PMML model. The utility of the proposed format and the scoring engine is evaluated by benchmarking the performance of the defect detection models on a range of different computational platforms.

Quality control is a fundamental component of many manufacturing processes, especially those involving casting or welding. However, manual quality control procedures are often time-consuming and error-prone. In order to meet the growing demand for high-quality products, the use of intelligent visual inspection systems is becoming essential in production lines. Recently, Convolutional Neural Networks (CNNs) have shown outstanding performance in both image classification and localization tasks. In this article, a system is proposed for the identification of casting defects in X-ray images, based on the Mask Region-based CNN architecture. The proposed defect detection system simultaneously performs defect detection and segmentation on input images, making it suitable for a range of defect detection tasks. It is shown that training the network to simultaneously perform defect detection and defect instance segmentation, results in a higher defect detection accuracy than training on defect detection alone. Transfer learning is leveraged to reduce the training data demands and increase the prediction accuracy of the trained model. More specifically, the model is first trained with two large openly-available image datasets before finetuning on a relatively small metal casting X-ray dataset. The accuracy of the trained model exceeds state-of-the art performance on the GRIMA database of X-ray images (GDXray) Castings dataset and is fast enough to be used in a production setting. The system also performs well on the GDXray Welds dataset. A number of in-depth studies are conducted to explore how transfer learning, multi-task learning, and multi-class learning influence the performance of the trained system.