Unsupervised surface defect detection using dictionary-based sparse representation

The design and study of pulsed eddy current sensors for detecting surface defects in small-diameter rods are highly significant. Accurate detection and identification of surface defects in small-diameter rods may be attained by the ongoing optimization of sensor design and enhancement of detection technologies. This article presents the construction of a non-coaxial differential eddy current sensor (Tx-Rx sensor) and examines the detection of surface defects in a small diameter bar. A COMSOL 3D model is developed to examine the variations in eddy current distribution and defect signal characteristics between the plate and rod components. The position of the excitation coil on the bar and the eddy current disruption around the defect are examined. Additionally, a Tx-Rx sensor has been developed and enhanced concerning coil dimensions, coil separation, and elevation height. An experimental system is established to detect bar structures with surface defects of varying depths, and a model correlating differential signal attenuation with defect depth is proposed, achieving a quantitative relative error of less than 5%, thereby offering a reference for the quantitative detection of bar surface defects.

Surface defects in manufacturing are top challenges in various manufacturing field including LED manufacturing, die manufacturing and printing industry. Quality control through automated surface defect detection has been an emphasis to speed up the production without jeopardizing the quality of the product. However, complexity and flexibility in product design, specification and dataset availability posted challenges in existing referential-based algorithm. Golden template-based algorithms are sensitive to misalignment and product variations. Deep learning and its variant can be used as non-linear filter to segment anomalies area. However, deep learning requires huge labelled database and consume long learning time. Similarly, maximum likelihood-based algorithms require large database for learning. This research proposes a novel histogram distance based multiple templates anomalies detection (MTAD) algorithm to segment surface defect. Histogram distance based on kernel-wise histograms stacked across illumination normalized database of similar size can describe the degree of anomaly intuitively across the image. Then, surface defect can be justified intuitively according to anomaly heat map generated. The algorithm is tested against industrial samples and it can handle texture and design variation existed in the product while catching anomaly in real time. This research suggests future studies on extending dimensionality of the histogram. Suggested algorithm has wide range of application other than surface defect detection. For examples, video motion detection, decolorization detection on industrial lighting.

Autoencoder-based anomaly detection for surface defect inspection

This study proposes a novel defect detection method to address the low accuracy and insufficient efficiency encountered during surface defect detection on aeroengine turbine blades (ATBs). The proposed approach employs the LDconv model to adjust the size and shape of convolutional kernels dynamically, integrates the deformable attention mechanism (DAT) to capture minute defect features effectively, and uses Focaler-CIoU to optimize the bounding box loss function of the detection network. Our approaches collectively provide precise detection of surface defects on ATBs. The results show that the proposed method achieves a mean average precision (mAP0.5) of 96.2%, an F-measure of 96.7%, and an identification rate (Ir) of 98.8%, while maintaining a detection speed of over 25 images per second. The proposed method meets the stringent requirements for accuracy and real-time performance in ATB surface defect detection.

Electrolytic capacitor surface defect detection based on deep convolution neural network

QRNet: Query-based reparameterization net for real-time detection of power adapter surface defects

Accurate detection of road surface defects and their integration into geospatial representations are key requirements for scalable UAV-based inspection and maintenance systems.This work presents a lightweight processing pipeline that converts image-based pavement defect segmentations into compact geospatial vector representations suitable for integration with GIS-driven inspection workflows. In addition, we introduce and publicly release a UAV-based road defect dataset with pixel-level annotations, specifically designed for crack-like pavement damage. A deep convolutional neural network is trained to perform semantic segmentation of pavement defects using images derived from the publicly available RDD2022 dataset. Segmentation performance is evaluated across a range of probability thresholds using standard pixel-wise metrics, and a validation-selected operating point is used to generate binary defect masks. These masks are subsequently processed to identify individual defect instances and extract vector polygons that preserve the underlying geometry of crack-like structures. For illustrative geospatial integration, predicted defects are projected into geographic coordinates and exported in standard GIS formats. By transforming dense segmentation outputs into compact georeferenced polygons, the proposed framework bridges deep learning-based perception and GIS-based infrastructure assessment, enabling instance-level geometric analysis and providing a practical representation for UAV-based road inspection scenarios.

Particleboard surface defect detection technology is of great significance to the automation of particleboard detection, but the current detection technology has disadvantages such as low accuracy and poor real-time performance. Therefore, this paper proposes an improved lightweight detection method of You Only Live Once v5 (YOLOv5), namely PB-YOLOv5 (Particle Board-YOLOv5). Firstly, the gamma-ray transform method and the image difference method are combined to deal with the uneven illumination of the acquired images, so that the uneven illumination is well corrected. Secondly, Ghost Bottleneck lightweight deep convolution module is added to Backbone module and Neck module of YOLOv5 detection algorithm to reduce model volume. Thirdly, the SELayer module of attention mechanism is added into Backbone module. Finally, replace Conv in Neck module with depthwise convolution (DWConv) to compress network parameters. The experimental results show that the PB-YOLOv5 model proposed in this paper can accurately identify five types of defects on the particleboard surface: Bigshavings, SandLeakage, GlueSpot, Soft and OliPollution, and meet the real-time requirements. Specifically, recall, F1 score, mAP@.5, mAP@.5:.95 values of pB-Yolov5s model were 91.22%, 94.5%, 92.1%, 92.8% and 67.8%, respectively. The results of Soft defects were 92.8%, 97.9%, 95.3%, 99.0% and 81.7%, respectively. The detection of single image time of the model is only 0.031 s, and the weight size of the model is only 5.4 MB. Compared with the original YOLOv5s, YOLOv4, YOLOv3 and Faster RCNN, the PB-Yolov5s model has the fastest Detection of single image time. The Detection of single image time was accelerated by 34.0%, 55.1%, 64.4% and 87.9%, and the weight size of the model is compressed by 62.5%, 97.7%, 97.8% and 98.9%, respectively. The mAP value increased by 2.3%, 4.69%, 7.98% and 13.05%, respectively. The results show that the PB-YOLOV5 model proposed in this paper can realize the rapid and accurate detection of particleboard surface defects, and fully meet the requirements of lightweight embedded model.

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.

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

Patch-type wearable electrocardiography and impedance pneumography for sleep staging: A multi-modal deep learning approach.

At present, the detection of surface defects of paper-plastic composite bags still mainly depends on manual visual inspection, which is very inefficient and easy to cause false detection. Based on the algorithm which combines edge detection and adaptive region growth, binary images of the surface defect areas is extracted, six types of shape features and seven types of invariant moment features are defined by calculation as the basis to complete the effective extraction of the surface features, then a paper-plastic composite bags surface defect detection platform is built to complete the defect detection experiment, the defect screening experiment was completed by the rapid screening method of its surface defect image based on gradient projection difference. At the same time, based on Genetic Algorithm (GA), Particle Swarm Optimization, and Grey Wolf Optimization, parameter optimization models of Support Vector Machine were established, respectively. Through experimental comparison, some results show that the defect detection and classification accuracy rate reach 96.83% based on the GA, and the detection speed with the screening method is 3.75 times faster than that without the screening method. Therefore, the reliability of the image classification and screening method for bags surface defects proposed in this study is verified.

Internal defects detection and classification in hollow cylindrical surfaces using single shot detection and MobileNet

Carbon fiber reinforced polymer (CFRP) has become an essential structural material in aerospace, new energy, rail transportation, and other fields due to its lightweight and high-strength properties. However, its complex manufacturing processes and demanding service environments can lead to various types of damage on both the surface and inside the material, significantly compromising safety. Existing detection techniques often adopt a step-by-step inspection mode, which results in complex processes and makes it difficult to achieve cross-dimensional correlation analysis of defects, leading to blind spots in structural health assessment. To address these issues, this paper proposes a method for simultaneous detection of surface and subsurface defects in CFRP based on infrared polarization imaging. First, we developed an infrared polarization imaging-based defect detection system and collected a CFRP defect dataset of samples containing various surface and subsurface defects. Then, we proposed a surface and subsurface defect detection network, which integrates extracted thermal diffusion features and polarization features to decouple and enhance surface and subsurface features. Through the constraints of multi-task defect detection, simultaneous detection of surface and subsurface defects is achieved. The experiments on the collected CFRP defect dataset demonstrate the effectiveness of the proposed method.

For the detection of wood surface defects, a convolutional neural network has a low detection efficiency and insufficient generalization ability, so it does not meet the requirements of online detection. Aiming to solve the above problems, the YOLOv3 baseline model, which has the advantage of multi-objective dynamic detection, was improved and applied to the online detection of wood surface defects. To solve the problem of the poor generalization ability of the network, GridMask was used to enhance the data and improve the robustness of the network. In order to solve the problem of the considerable amount of network parameter calculations and insufficient real-time performance, the residual block of the backbone network was changed to a Ghost block structure to achieve a lightweight model. Finally, the confidence loss function of the network was improved to reduce the influence of simple samples and negative samples on model convergence. The experimental results showed that, compared with the original network, the improved algorithm increased the mean average precision by 5.73% and the detection speed was increased to 28 frames per second (an increase of 11), which met the requirements for real-time industrial detection.