An imbalanced small sample slab defect recognition method based on image generation

Electrolytic capacitor surface defect detection based on deep convolution neural network

With the development of industrial economy, more and more enterprises use machine vision and artificial intelligence to replace manual detection. Therefore, the research of steel surface defect detection based on artificial intelligence is of great significance to promote the rapid development of intelligent factory and intelligent manufacturing system. In this paper, Yolov5 deep learning algorithm is used to build a classification model of steel surface defects to realize the classification and detection of steel surface defects. At the same time, on the basis of Yolov5, combined with the attention mechanism, the backbone network is improved to further improve the classification model of steel surface defects. The experiment shows that the Recall and mAP of improved Yolov5 perform better on the steel surface defect data set. Compared with Yolov5, the number of C3CA-Yolov5 parameters decreased by 13.02%, and the size of pt files decreased by 12.72%; the number of C3ECA-Yolov5 parameters decreased by 13.36%, and the size of pt files decreased by 13.22%.

The classification of steel surface defects plays a very important role in analyzing their causes to improve manufacturing process and eliminate defects. However, defective samples are very scarce in actual production, so using very few samples to construct a good classifier is a challenge to be addressed. If the layer number of the model with proper depth is increased, the model accuracy will decrease (not caused by overfit), and the training error as well as the test error will be very high. This is called the degradation problem. In this paper, we propose to use feature extraction + feature transformation + nearest neighbors to classify steel surface defects. In order to solve the degradation problem caused by network deepening, the three feature extraction networks of Residual Net, Mobile Net and Dense Net are designed and analyzed. Experiment results show that in the case of a small sample number, Dense block can better solve the degradation problem caused by network deepening than Residual block. Moreover, if Dense Net is used as the feature extraction network, and the nearest neighbor classification algorithm based on Euclidean metric is used in the new feature space, the defect classification accuracy can reach 92.33% when only five labeled images of each category are used as the training set. This paper is of some guiding significance for surface defect classification when the sample number is small.

Quality control in metal product manufacturing relies heavily on accurately detecting and classifying surface defects through visual inspection. Recently, convolutional neural networks (CNNs) have shown promising results in automating this process with high accuracy. This research paper proposes a new (experimental version) Lite Convolutional Neural Network (LCNN) designed to analyze image data to detect and classify surface defects on metallic surfaces. Our model was trained on a metal surface defects dataset comprising 1800 images of six different types of surface defects. Despite using relatively small datasets, the proposed LCNN version achieves a classification accuracy of 91.67%, highlighting its effectiveness in real-world defect detection scenarios.

The automatic detection and recognition of steel surface defects is very important in the steel manufacturing industry based on the classification of defect types using artificial intelligence. Deep learning plays an important role to decrease the defection rate in the steel manufacturing industry. Defects in the surface of steel have a serious effect on the quality of steel. Previous research for the NEU-DET dataset has shown that there are some limitations, such as low detection accuracy. In this paper Feature Pyramid Network (FPN) + Resnet neural network has been proposed for detecting the overlapping and multiple defects in the complex background for improving the defect detection rate. The histogram and edge detection approach is used for feature extraction for the classification of defects. The final result shows that the proposed FPN + Resnet model trained with good steel surface defect detection performance, and the dice score is 0.7963, IoU score is 0.6818 and losses is 0.0522 which is very low as compared to others. The proposed detection approach can efficiently detect minor targeted defects on the steel surface, which can be used as a benchmark for automated steel surface defect identification.

Machine vision systems with effective image processing methods are used in quality grading of agricultural products. A pattern recognition technique was developed to detect and classify surface defects such as pitting, splitting and stem-end rot found in images of mandarin fruits. The developed technique employs fuzzy thresholding for image segmentation, binary wavelet transform (BWT) for feature extraction and a rule based linear classifier model for detection and classification of the defects. The moment invariants computed from the detail subimage of BWT were taken as feature values. This paper in detail describes about the pattern recognition algorithm and its implementation. The detection and classification results obtained from the algorithm are reported and discussed.

A nondestructive testing method for detecting surface defects of Si3N4-Bearing cylindrical rollers based on an optimized convolutional neural network

The detection of rail surface defects is an important tool to ensure the safe operation of rail transit. Due to the complex diversity of track surface defect features and the small size of the defect area, it is difficult to obtain satisfying detection results by traditional machine vision methods. The existing deep learning-based methods have the problems of large model sizes, excessive parameters, low accuracy and slow speed. Therefore, this paper proposes a new method based on an improved YOLOv4 (You Only Look Once, YOLO) for railway surface defect detection. In this method, MobileNetv3 is used as the backbone network of YOLOv4 to extract image features, and at the same time, deep separable convolution is applied on the PANet layer in YOLOv4, which realizes the lightweight network and real-time detection of the railway surface. The test results show that, compared with YOLOv4, the study can reduce the amount of the parameters by 78.04%, speed up the detection by 10.36 frames per second and decrease the model volume by 78%. Compared with other methods, the proposed method can achieve a higher detection accuracy, making it suitable for the fast and accurate detection of railway surface defects.

Cylinder liner is an internal part of the automobile engine, which plays an important role in the automobile internal combustion engine. Therefore, it is a top priority to accurately and quickly detect the cylinder liner surface defects. In order to effectively achieve the classification and localization of surface defects on the cylinder liner, this paper establishes a dataset for surface defects on cylinder liner and proposes a based on improved YOLOv5 algorithm for detecting surface defects on cylinder liner. Firstly, a machine vision system is established to acquire on-site images and perform manual annotation to build the dataset of surface defects on cylinder liner. Secondly, the GSConv SlimNeck mechanism is introduced to reduce the model complexity; the Bi-directional Feature Pyramid Network (BiFPN) is used to fuse the feature information at different scales to enhance the detection accuracy of small surface defects on cylinder liner; and embedding the SimAM attention mechanism to focus on the object region of interest and improve the accuracy and robustness of the model. The final improved YOLOv5 model reduces the number of model parameters by 15.8% compared to the non-improved YOLOv5. And the experimental results on our self-built dataset for cylinder liner defects show that the mAP0.5 is improved by 0.4%. This means that the accuracy of model detection was not compromised. This method can be applied to actual production processes.

Nondestructive detection of surface defects of curved mosaic ceramics based on deep learning

Surface defect identification is a crucial task in many manufacturing systems, including automotive, aircraft, steel rolling, and precast concrete. Although image-based surface defect identification methods have been proposed, these methods usually have two limitations: images may lose partial information, such as depths of surface defects, and their precision is vulnerable to many factors, such as the inspection angle, light, color, noise, etc. Given that a three-dimensional (3D) point cloud can precisely represent the multidimensional structure of surface defects, we aim to detect and classify surface defects using a 3D point cloud. This has two major challenges: (i) the defects are often sparsely distributed over the surface, which makes their features prone to be hidden by the normal surface and (ii) different permutations and transformations of 3D point cloud may represent the same surface, so the proposed model needs to be permutation and transformation invariant. In this paper, a two-step surface defect identification approach is developed to investigate the defects’ patterns in 3D point cloud data. The proposed approach consists of an unsupervised method for defect detection and a multi-view deep learning model for defect classification, which can keep track of the features from both defective and non-defective regions. We prove that the proposed approach is invariant to different permutations and transformations. Two case studies are conducted for defect identification on the surfaces of synthetic aircraft fuselage and the real precast concrete specimen, respectively. The results show that our approach receives the best defect detection and classification accuracy compared with other benchmark methods.

As a classical research direction in the field of computer vision, anomaly detection has a very wide range of application prospects. Surface defect detection is an extremely important part of the industrial production process. Most of the traditional defect detection solutions are based on machine vision or supervised learning paradigms. These methods require the use of a large number of supervised defect samples, but it is difficult to obtain sufficient defect data in the production process. Due to various random factors, it is not easy to identify all types of defects during the inspection phase. With the development of deep unsupervised learning in recent years, autoencoder or generative adversarial networks are widely used in surface defect detection problem, which rely solely on the modeling of good data to discriminate abnormal defects. Therefore, in this paper, we propose a neural architecture search-based defect detection method. We combine neural architecture search and generative adversarial learning to automate the search of encoder-decoder structures with a gradient optimization-based search method. The method learns a pair of an anomalous image and its anomaly-free reconstruction, while simultaneously learning a decision boundary between normal and anomalous examples. Neural architecture search helps to search for a task-appropriate network architecture with better performance. Finally, the proposed method is evaluated on the industrial inspection dataset MVTec AD, and the effectiveness of the model detection is measured by AUROC metrics, demonstrating the validity of the methods is demonstrated by both quantitative and qualitative analysis.

In the context of industrial hot-rolled strip steel surface defect detection, where the demands for real-time performance and classification accuracy are paramount, we present EAF-DenseNet121–a lightweight, enhanced model that incorporates edge-entropy attention mechanisms. At the inception of the DenseNet121 architecture, we incorporate a learnable Sobel-based edge extraction branch, which is designed to adaptively delineate defect contours with precision. We have designed an Entropy-Attention Fusion (EAF) module to further refine the model’s performance. This module constructs a four-dimensional tensor, integrating the primary feature map, edge map, and their corresponding local entropy maps. By applying dual-path channel-wise and spatial attention, we achieve a weighted fusion of information, thereby enriching the feature representation. The EAF module replaces three pivotal convolutional layers within the DenseNet framework–immediately following the initial convolution and subsequent to the first and second Transition layers. This replacement enhances feature representation with a negligible increase in additional parameters, leading to a substantial improvement in defect recognition and classification accuracy. Our experimental results, obtained on the NEU-DET dataset, reveal that the enhanced model achieves a classification accuracy of 99.17%, representing an improvement of 2.78% over the baseline. Furthermore, on the GC10-DET dataset, the model achieves a classification accuracy of 82.89%, further validating its strong generalization capabilities.

Plant disease can seriously affect the growth and development of plants, resulting in reduced production and even death. Disease control can assist in plant breeding and cultivation, ensuring crop yield and quality. But traditional disease control methods are increasingly difficult to meet modern time, space and cost requirements. Deep learning technology has developed rapidly in recent years; it can improve the efficiency of plant disease diagnosis and detection, and greatly reduce the risk of human intervention and misjudgment. However, challenges such as data acquisition, environmental interference, and model deployment complexity hinder the application of deep learning in plant disease control. Therefore, there is an urgent need for disease feature optimization algorithms to protect current large-scale agricultural production.This research topic provides a platform for sharing the latest research results of deep learning in control of plant disease. The focus on the progress of deep learning technology in this field mainly involves the application of advanced technology in plant disease feature adaptation. This research topic aims to explore the latest research and application of deep learning technology in plant disease identification and control, focusing on: 1) identification techniques for early plant disease, 2) prediction and prevention of the spread of plant disease, 3) new methods for collecting multi-source plant disease image data, 4) quantitative evaluation of plant damage, 5) real-time application deployment based on embedded devices and edge wearable devices, 6) adaptive image processing methods for different application environments.A study by Le Yang et al. explored a new maize weed recognition model, SE-VGG16, and applied the SE-VGG16 model to weed detection of other species to build a weed detection model with the ability to generalize weed control in agricultural production processes. SE-VGG16 model is based on VGG16, adding SE attention mechanism. The model implements automatic focusing and allocates limited information processing resources to important parts. It has the characteristics of high efficiency, stability and high detection accuracy.Pushkar Gole et al. focused on lightweight visual converter networks in a study of automatic plant disease recognition. This study mainly introduces two tasks: one is to replace a multilayer perceptron (MLP) with the initial module and reconstruct the transformer Inception module to reduce the computational complexity of the vision transformer (ViT) model. In addition, the proposed new network is trained and tested on the PlantVillage dataset and the field maize image dataset, which proves its applicability in real scenarios.Further, Xin Xu et al. studied a cotton moth infestation monitoring method. In this study, five different models of cotton aphid infestation identification were constructed, trained and tested, among which YOLOv5 model had the best performance. The real-time identification system established in this study can provide a faster and more convenient technical means for the monitoring of cotton aphid infection.In another article, Nak Jung Choi et al. focused on identifying and tracking the behavior, movement, size, and habits of different species of insects by building a 3D monitoring system. While traditional 2D monitoring systems are static and ignore Zaxis depth dimensions, 3D systems are able to track insect movement more comprehensively, providing valuable depth dimension insights.Another study by Jitong Cai et al., explored a lightweight CNN model, FCA-EfficientNet, to achieve accurate identification of multiple maize disease. The work introduced autofocus modules and FCA modules to filter out background noise, allowing the network to focus on disease areas. It also makes the model more lightweight by removing redundant network structures.In addition, Fei Nan et al. studied the classification of maize disease from another angle. They focused on a deep convolutional neural network with RGB-D images. Among them, a variety of improved data preprocessing methods improved the accuracy and speed of maize diseases image recognition.A study by Zhenghang Zhang et al. explored the potential of applying Generative Adversarial Networks (GANs) to the diagnosis of cotton fusarium wilt. This study designed a model based on small sample learning and proposed an innovative cotton verticillium wilt diagnosis system. The convolutional neural network is used as feature extractor, and the trained GANs model is used for sample enhancement to improve the classification accuracy.In summary, these findings highlight the significant advances that deep learning technology has made in identifying and controlling plant disease in the information age. In the future, these models can be deployed in smart agriculture systems to monitor and identify plant disease in real time, so that appropriate control measures can be taken in a timely manner. As deep learning technology continues to evolve and improve, we can expect these models to play an increasingly important role in plant disease control, providing more effective support for agricultural production.

Steel defect detection is a crucial aspect of steel production and quality control. Therefore, focusing on small-scale defects in complex production environments remains a critical challenge. To address this issue, we propose an innovative perception-efficient network designed for the fast and accurate detection of multi-scale surface defects. First, we introduce the Defect Capture Path Aggregation Network, which enhances the feature fusion network's ability to learn multi-scale representations. Second, we design a Perception-Efficient Head (PEHead) to effectively mitigate local aliasing issues, thereby reducing the occurrence of missed detections. Finally, we propose the Receptive Field Extension Module (RFEM) to strengthen the backbone network's ability to capture global features and address extreme aspect ratio variations. These three modules can be seamlessly integrated into the YOLO framework. The proposed method is evaluated on three public steel defect datasets: NEU-DET, GC10-DET, and Severstal. Compared to the original YOLOv8n model, PEYOLO achieves mAP50 improvements of 3.5%, 9.1%, and 3.3% on these datasets, respectively. While maintaining similar detection accuracy, PEYOLO retains a high inference speed, making it suitable for real-time applications. Experimental results demonstrate that the proposed PEYOLO can be effectively applied to real-time steel defect detection.