Detection of defects in atomic-resolution images of materials using cycle analysis

In this paper, we use the active contour models (Snakes) for edge detection and segmentation of weld defects in radiographic images. Gradient Vector Flow snakes enhance the concave object extraction capability. However, the GVF snakes are sensitive to noise. Several new snake models were developed by combining different methods with GVF snake. Here, a multiscale GVF and B-spline model is proposed to overcome the traditionnal GVF dis-adventage. Experiments on synthetic and radiographic images are promoising

Given that defect detection in weld X-ray images is a critical aspect of pressure vessel manufacturing and inspection, accurate differentiation of the type, distribution, number, and area of defects in the images serves as the foundation for judging weld quality, and the segmentation method of defects in digital X-ray images is the core technology for differentiating defects. Based on the publicly available weld seam dataset GDX-ray, this paper proposes a complete technique for fault segmentation in X-ray pictures of pressure vessel welds. The key works are as follows: (1) To address the problem of a lack of defect samples and imbalanced distribution inside GDX-ray, a DA-DCGAN based on a two-channel attention mechanism is devised to increase sample data. (2) A convolutional block attention mechanism is incorporated into the coding layer to boost the accuracy of small-scale defect identification. The proposed MAU-Net defect semantic segmentation network uses multi-scale even convolution to enhance large-scale features. The proposed method can mask electrostatic interference and non-defect-class parts in the actual weld X-ray images, achieve an average segmentation accuracy of 84.75% for the GDX-ray dataset, segment and accurately rate the valid defects with a correct rating rate of 95%, and thus realize practical value in engineering.

With the progression of deep learning algorithms in computer vision, a lot of research is taking place in the semiconductor industry towards improving real-time defect detection and classification analysis. An Automated Defect Classification and Detection (ADCD) framework not only enables rapid measurement of dimensions and classification of defects, but also helps minimize production costs, engineering time as well as tool cycle time associated with the defect inspection process. As we continue to shrink the pitch (below 36nm), defect characterization at wafer scale becomes a key issue as it demands rapid measurement but without losing accuracy and repeatability. Also, in the context of high NA lithography (thin resist), accurate metrology becomes difficult with very noisy as well as low contrast images (No BKM exists till now). Human eyes generally demonstrate close to the Bayesian Error limit in detecting smaller objects (for example, extracting contextual information instantaneously from nanoscale defects in SEM images). However, for most One-stage and Two-stage object detectors, this is still a very challenging task due to variable image resolution and SEM (scanning electron microscope) image quality (low SNR). In this research work, we have experimented with different modified YOLOv5 object detectors to improve challenging stochastic defect detection precision. In this work, we have proposed an ensemble strategy by empirically combining multiple custom-trained models (YOLOv5n, YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x) together at the test and inference time. We have noticed four YOLOv5 architecture variants are outperforming against our previous Ensemble ResNets model with improvements of the average precision metric (AP) of the most difficult defect classes as p gap and microbridges as well as overall mAP accuracy. With Ensemble YOLOv5, the p gap AP and microbridge AP metrices have been improved by 35% and 25.33%, respectively, whereas the overall mAP has been improved by 6.25%. The proposed Automated Defect Classification and Detection (ADCD) framework can also be used for high resolution and high-speed metrology, providing rapid identification of defects with improved certainty and further root cause investigation.

UAV patrol inspection is a new patrol inspection method to complete the maintenance of overhead transmission line by using unmanned aircraft for navigation and shooting and relying on the advantages of independent operation. Compared with the traditional aerial patrol, UAV patrol has the advantages of strong adaptability, high safety factor, low risk and low cost. However, there are image defects and other methods in the process of application. Therefore, in the face of this situation, it is necessary to design an image defect detection method for aviation insulators based on deep learning. Creating the insulator image acquisition and deep learning environment, determined the image segmentation detection threshold under deep learning, and located the insulator image defect detection fault. The Crop-MobileNet network detection model is established, and the CNN processing method is used to detect the insulator defects in aerial photography. The final test results show that under different deep learning convolution ranges, compared with the traditional scaling factor defect detection group, the deep learning image defect detection group has a higher recall rate. It shows that the defect detection effect of aerial images is relatively good, which has practical significance.

This paper presents a survey on latest image segmentation techniques using homogeneity. Homogeneity is one of the most widely used approaches for image segmentation because of its robust characteristics for texture segmentation. The existing image segmentation approaches suffer from the problem of over segmentation and leave a scope for enhancing accuracy of segmentation. To address the drawbacks of conventional image segmentation approaches homogeneity based approaches can be used which deal with image texture and thus provide better segmentation results. This paper focuses on local homogeneity based approaches for image segmentation and image defect detection. For this the approaches like image local homogeneity analysis with region merging, local homogeneity analysis with discrete cosine transform, local homogeneity analysis with wavelet transform, homogeneity with FFD method, homogeneity with color features, local homogeneity with Gabor filtering and homogeneity with watershed algorithm are used.

In addition to causing damage to vehicles, road defects are one of the main causes of vehicle accidents which lead to loss of human lives. Many methods of detecting defects have been introduced over the years to reduce the consequences of these defects. One of these methods is image processing. Use of image and video processing has many applications in medicine, science, agriculture, and defect detection in structures. It has been used for defect detection on roads because timely detection and analysis of defect is very important for road serviceability and safety of the people. Detection of a defect by image processing broadly follows some of the basic steps which include feature extraction, edge detection, morphological operators, and training of data. Different approaches are used for various kinds of defect detection and analysis which have replaced the manual inspection method of roads saving time and resources. This chapter discusses the basic steps involved in defect detection using image processing along with existing systems that use machine learning and artificial intelligence for the detection of defects from a distance. To write this chapter, papers on the topic of image and computer vision-based defect detection systems have been consulted.

Crystallographic defects can now be routinely imaged at atomic resolution with aberration-corrected scanning transmission electron microscopy (STEM) at high speed, with the potential for vast volumes of data to be acquired in relatively short times or through autonomous experiments that can continue over very long periods. Automatic detection and classification of defects in the STEM images are needed in order to handle the data in an efficient way. However, like many other tasks related to object detection and identification in artificial intelligence, it is challenging to detect and identify defects from STEM images. Furthermore, it is difficult to deal with crystal structures that have many atoms and low symmetries. Previous methods used for defect detection and classification were based on supervised learning, which requires human-labeled data. In this work, we develop an approach for defect detection with unsupervised machine learning based on a one-class support vector machine (OCSVM). We introduce two schemes of image segmentation and data preprocessing, both of which involve taking the Patterson function of each segment as inputs. We demonstrate that this method can be applied to various defects, such as point and line defects in 2D materials and twin boundaries in 3D nanocrystals.

In this research work, we have demonstrated the application of Mask-RCNN (Regional Convolutional Neural Network), a deep-learning algorithm for computer vision and specifically object detection, to semiconductor defect inspection domain. Defect detection and classification during semiconductor manufacturing has grown to be a challenging task as we continuously shrink circuit pattern dimensions (e.g., for pitches less than 32 nm). Current state-of-the-art optical and e-beam inspection tools have certain limitations as these tools are often driven by some rule-based techniques for defect classification and detection. These tool/software limitations often lead to misclassification which necessitates manual classification. In this work, we have revisited and extended our previous deep learning-based defect classification and detection method [1] for improved defect instance segmentation in SEM images with precise extent of defect as well as generating a mask for each defect category/instance. This also enables to extract and calibrate each segmented mask and quantify the pixels that make up each mask, which in turn enables us to count each categorical defect instances as well as to calculate the surface area in terms of pixels. This paper aims at detecting and segmenting different types of defect patterns such as bridges, breaks and line collapse as well as to differentiate accurately between multi-categorical defect bridge scenarios (as thin/single/multi-line/horizontal/non-horizontal) for aggressive pitches as well as thin resists (High NA applications). Our proposed approach demonstrates its effectiveness both quantitatively and qualitatively.

This paper presents a novel method for detection and recognition of glass defects in low resolution images. First, the defect region is located by the method of Canny edge detection, and thus the smallest connected region (rectangle) can be found. Then, the binary information of the core region can be obtained based on a specific filter. After noises are removed, a novel Binary Feature Histogram (BFH) is proposed to describe the characteristic of the glass defect. Finally, the AdaBoost method is adopted for classification. The classifiers are designed based on BFH. Experiments with 800 bubble images and 240 non-bubble images prove that the proposed method is effective and efficient for recognition of glass defects, such as bubbles and inclusions.

Diagnostics of composite castings, due to their complex structure, requires that their characteristics are tested by an appropriate description method. Any deviation from the specific characteristic will be regarded as a material defect. The detection of defects in composite castings sometimes is not sufficient and the defects have to be identified. This study classifies defects found in the structures of saturated metallic composite castings and indicates those stages of the process where such defects are likely to be formed. Not only does the author determine the causes of structural defects, describe methods of their detection and identification, but also proposes a schematic procedure to be followed during detection and identification of structural defects of castings made from saturated reinforcement metallic composites. Alloys examination was conducted after technological process, while using destructive (macroscopic tests, light and scanning electron microscopy) and non-destructive (ultrasonic and X-ray defectoscopy, tomography, gravimetric method) methods. Research presented in this article are part of author’s work on castings quality.

Fabric defect detection is a key part to ensure quality of product in textile industry. The paper addressed on structure design and implementation of real-time fabric defect detection system based on Gabor filtering. The system mainly consists of three parts of image acquisition, defect detection and defect classification. Defect detection is core of whole system, the basic structure of which is PCIbased image data transmission as well as process system based on FPGA and external RAM. The Gabor filtering algorithm is used for defect detection, which is implemented with high performance FPGA assisted by external RAM to buffer image data. The CCD camera based rapid high-resolution image acquisition, high-speed PCI transmission as well as defect detection algorithm implemented with FPGA meet real-time needs of system. Practices show that the system can accurately detect more than 20 kinds of fabric defects in real time. When the resolution of input image is 2048×512 and fabric speed is 60 m/s, defect detection accuracy can be up to 0.5mm and accuracy about 90%.

Defects are unavoidable in casting production owing to the complexity of the casting process. While conventional human-visual inspection of casting products is slow and unproductive in mass productions, an automatic and reliable defect detection not just enhances the quality control process but positively improves productivity. However, casting defect detection is a challenging task due to diversity and variation in defects' appearance. Convolutional neural networks (CNNs) have been widely applied in both image classification and defect detection tasks. Howbeit, CNNs with frequentist inference require a massive amount of data to train on and still fall short in reporting beneficial estimates of their predictive uncertainty. Accordingly, leveraging the transfer learning paradigm, we first apply four powerful CNN-based models (VGG16, ResNet50, DenseNet121, and InceptionResNetV2) on a small dataset to extract meaningful features. Extracted features are then processed by various machine learning algorithms to perform the classification task. Simulation results demonstrate that linear support vector machine (SVM) and multi-layer perceptron (MLP) show the finest performance in defect detection of casting images. Secondly, to achieve a reliable classification and to measure epistemic uncertainty, we employ an uncertainty quantification (UQ) technique (ensemble of MLP models) using features extracted from four pre-trained CNNs. UQ confusion matrix and uncertainty accuracy metric are also utilized to evaluate the predictive uncertainty estimates. Comprehensive comparisons reveal that UQ method based on VGG16 outperforms others to fetch uncertainty. We believe an uncertainty-aware automatic defect detection solution will reinforce casting productions quality assurance.

This paper presents an advanced defect detection system for wire Electrical Discharge Machining (EDM), utilizing Convolutional Neural Networks (CNNs) to automatically identify, classify, and localize defects such as cracks, notches, and burrs. Wire EDM is a precision manufacturing process critical for cutting conductive materials, where defect detection plays a vital role in ensuring product quality. The proposed method incorporates a modified ResNet-50 architecture, optimized specifically for defect detection in wire EDM. The architecture leverages deep residual learning to enhance feature extraction, allowing the system to detect minute defects effectively. A dataset of 10,000 RGB images (224 × 224 pixels) was used for training, with the model achieving an impressive 95.3% accuracy, 94.2% recall, 95.8% precision, and 94.7% F1 score on the test set. The system demonstrated excellent performance in detecting cracks, though it showed slightly lower performance on deformation-related defects. A comprehensive comparison with traditional defect detection methods and other deep learning models underscores the superiority of the proposed approach in terms of both accuracy and robustness. The results indicate that this CNN-based system offers a reliable and efficient solution for quality control in wire EDM processes. Future research will focus on further optimizing the network for real-time defect detection and extending the approach to incorporate multi-modal data, such as sensor and acoustic signals, to improve overall detection performance.

Image segmentation algorithms applied to wood defect detection

In this paper, we present a printed circuit board (PCB) inspection system based on using Hausdorff distance for image alignment and defect detection. In addition, we apply support vector machine (SVM) for the defect classification and the metal classification in this system. The three major components in the proposed PCB inspection system consist of image alignment, defect detection, and defect classification. In image alignment, a coarse-to-fine search technique is applied to accelerate the speed of finding the minimal Hausdorff distance between the reference and the inspection images. For defect detection, we calculate the Hausdorff distance of every pixel in the inspection image as the first step and compare the result with a predefined threshold. For the cases where the computed Hausdorff distance is greater than the threshold, the location of that pixel is labeled as a defect suspect. The existence of defect then can be confirmed by merging the nearby suspects into one object. For defect classification, the local image features are extracted and passed to support vector machine for training and identifying defect types. In this work, we focus on distinguishing the type of a defect as one of open, short, pinhole, over-etch, or under-etch types. Support vector machine can be applied to metal classification as well. At the current stage, we supply support vector machine with RGB color information as the feature vector for metal classification. Experimental results show that the Hausdorff distance based method detects defects in a printed circuit board efficiently and accurately, and the support vector machine approach also gives satisfactory results for both defect and metal classifications.