检索结果-内蒙古大学图书馆

FFDDNet: Flexible Focused defect detection Network

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Lin, Zeyu Li, Ziyang Yu, Jiong Hu, Mengzi Wang, Xin Xinjiang Univ Sch Software Urumqi 890091 Peoples R China

It is an important research area to optimize object detection methodology for improving the performance of steel surface defect detection. However, existing research is suffering from the problem of non-rigid deformation, background noise interference, and low detection efficiency. To address this problem, we propose an end-to-end flexible focused defect detection network (FFDDNet) in this article. First, we propose a restricted deformable convolutional network (RDCN) to efficiently extract the defect features, which makes the receptive field more fit the pixel area of the target image within the limited range and avoid excessive movement of the sampling points by designing a restricted function. Second, we propose the global vertical and horizontal attention (GVHA) to effectively reduce the interference of irrelevant background information, which consists of nested vertical and horizontal attention mechanism. Finally, we combine RDCN and GVHA to form a new convolution operator global RDCN (GRDCN) and apply to the information calculation of the new detection network FFDDNet to achieve accurate and efficient detection. Multiple experimental results on the NEU-DET dataset and GC10-DET dataset show that the mean average precision (mAP) of our proposed model increases by 8.5% and 3.6%, respectively compared with baseline and maintains a fast detection speed. It means FFDDNet effectively improves the efficiency of defect detection on surfaces. The source codes are available at: https://***/LinZeyu12/FFDDNet.

关键词： Convolution Feature extraction Steel Interference Accuracy Attention mechanisms Convolutional neural networks Surface treatment Deformation Attention mechanism deep learning defect detection deformable convolution deformable convolution

来源：评论

学校读者我要写书评

暂无评论

A Novel Incremental defect detection Method via Elastic Heterogeneous Distillation Network

引用

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING 2025年 22卷 10149-10161页

作者： Shen, Xiangkai Liu, Jinhai Zhang, Huaguang Jiang, Lin Zhao, He Yang, Hongyu Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China State Key Lab Synthet Automat Proc Ind Shenyang 110819 Peoples R China Natl Pipeline Network Grp Storage & Transportat Te Shenyang Branch Shenyang 110819 Peoples R China

In industrial processes, the defect data is continuously accumulated over time, and new classes of defects can arise at any time. When a well-trained model is adapted to new classes, its performance in old classes will sharply decline. To solve the above issue, a novel incremental defect detection method named elastic heterogeneous distillation network (EHD-Net) is proposed. First, an elastic knowledge transfer method is proposed to selectively transfer the core features of the old classes, so that the old knowledge is retained and new knowledge is effectively learned at the feature level. Second, warping heterogeneous distillation learning is proposed for the first time. In warping heterogeneous distillation learning, a gradient warping layer is proposed to balance the optimization direction of gradients for both old and new classes, and the proposed heterogeneous distillation learning strategy can clarify the association and difference between new and old classes, so that the rapid learning of new knowledge and comprehensive transfer of old knowledge are guaranteed at the decision level. Finally, a well-trained evolutionary model is employed to achieve the detection of both old and new classes. The proposed method can effectively overcome the catastrophic forgetting of old classes and guarantee the independent learning of new classes. Experimental results on two industrial datasets show that EHD-Net outperforms existing advanced methods. Note to Practitioners-The motivation for this paper is an important and highly practical issue called class-incremental defect detection. Specifically, new classes of defects always appear in industrial scenarios over time and when a well-trained detection model adapts to the new classes, its performance in the old classes decreases dramatically. To solve the above issues, an elastic heterogeneous distillation network (EHD-Net) via elastic knowledge transfer and warping heterogeneous distillation learning is proposed. The proposed

关键词： Feature extraction Adaptation models defect detection Knowledge transfer Accuracy Training Stability analysis Decision making Data models Optimization evolutionary model elastic heterogeneous distillation network (EHD-Net) incremental learning

来源：评论

学校读者我要写书评

暂无评论

AdaptiveDet: defect detection for Digital Printing Fabric with Complex Background

引用

JOURNAL OF NATURAL FIBERS 2025年第1期22卷

作者： Su, Zebin Zhang, Xingyi Li, Jiamin Shao, Yunlong Li, Pengfei Zhang, Huanhuan Xian Polytech Univ Sch Elect & Informat Jinhua South Rd 19 Xian 710048 Peoples R China Xian Polytech Univ Shaanxi Artificial Intelligence Joint Lab Xian Peoples R China

During the digital printing process, the fabric defects need to be accurately detected to ensure product quality. However, the defects are difficult to effectively distinguish from the background, which can cause degradation of detection model performance. To solve this problem, a defect detection model incorporating adaptive attention mechanisms, AdaptiveDet, was proposed for digital printing fabric. First, the initial anchor box was generated using the K-means++ algorithm to better adapt to the complex target shape. Second, the backbone network could be reconfigured using the adaptive CBS module, allowing higher-level features to be extracted and interference with non-critical features to be reduced. Then, the neck network was reconfigured using the ELAN-EVC module so that the model could learn both global and local feature representations to capture information more accurately about minor defects. Finally, the DyHead framework was adopted in the head of YOLOv7-Tiny to enhance the model's sensitivity to spatial information, which lead to excellent performance in the complex background defect detection task. The experimental results show that the proposed model performs well on the DPFD-DET dataset with mAP@.5 of 93%, which outperforms other detection models. This shows that it could meet the demand for high-precision defect detection for digital printing fabric. (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic). (sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic). (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)AdaptiveDet. (sic)(sic), (sic)(sic)K-means++(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)

关键词： Digital printing defect detection YOLOv7-tiny adaptive CBS ELAN-EVC module DyHead (sic)(sic)(sic)(sic) (sic)(sic)(sic)(sic) YOLOv7(sic)(sic) (sic)(sic)(sic)CBS ELAN-EVC(sic)(sic)

来源：评论

学校读者我要写书评

暂无评论

Automated fabric defect detection using multi-scale fusion MemAE

引用

VISUAL COMPUTER 2025年第1期41卷 723-737页

作者： Wu, Kun Zhu, Lei Shi, Weihang Wang, Wenwu Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan Peoples R China

Fabric defect detection (FDD) is an essential part of the textile industry. To replace manual visual inspection, computer-vision-based solutions has been widely investigated in both unsupervised or supervised manner during the past few decades. However, precisely locating defective regions, especially for those tiny and inconspicuous ones, is still challenging. To this end, we propose an unsupervised learning approach for FDD via multi-scale memory-augmented auto-encoder (MemAE) fusion. The architecture of the proposed CNN model follows an encode-decode style. On the one hand, we explore the defect-free region reconstruction ability of the shallow CNN layers. On the other hand, the reconstruction ability of defect region is much emphasized in the deep layers. In the training phase of the network, we only use defect-free samples to learn the visual features of normal fabric textural representation. In the testing phase, a defective image is expected to be unpainted during the inference, and we further emphasize the defect regions by computing the pixel-level residual maps between the defective image and its corresponding reconstructed version. Additionally, a coarse-to-fine scheme is proposed to precisely locate the defect region by first introducing KNN and DeepSVDD to coarsely localize the defects, followed by a finer refinement using the obtained residual map. The proposed method is evaluated on two different types of datasets: the Periodic-pattern fabric database and the Yarn-dyed fabric database. The experimental results illustrate that our method consistently outperforms the state-of-the-art methods in terms of quality and robustness in both types of datasets with certain margin.

关键词： defect detection Memory-augmented auto-encoder Multi-scale fusion DeepSVDD

来源：评论

学校读者我要写书评

暂无评论

Thermal Imaging for Quality Control in Thin Silicon-Based Coatings for Lithium-Ion Batteries: defect detection, Drying Dynamics, and Machine Learning-Based Mass Loading Estimation

引用

SMALL METHODS 2025年 e2402079页

作者： Amin, Adil Geiping, Philipp Valentin Odungat, Ahammed Suhail Oezcan, Fatih Segets, Doris Inst Energy & Mat Proc Particle Sci & Technol EMPI Carl Benz Str 199 D-47057 Duisburg Germany Univ Duisburg Essen UDE Ctr Nanointegrat Duisburg Essen CENIDE Carl Benz Str 199 D-47057 Duisburg Germany

This study demonstrates thermal imaging as a non-destructive, real-time quality-control-method for detecting coating defects, analyzing mass loading, and understanding drying dynamics in silicon-based thin coatings. Thermal imaging identifies critical defects such as streaks, pinholes, and chatter marks through distinct thermal signatures, with streaks reducing surface temperature by up to 15 degrees C. It establishes strong correlations between surface temperature, mass loading, and coating thickness: for instance, a 100 mu m wet film thickness shows a surface temperature of approximate to 50 degrees C, corresponding to a mass loading of 2.4 mg cm(-)2. Drying dynamics reveal that thicker coatings retain more solvent, prolong drying, and shrink significantly, with 100 mu m wet-gap coatings shrinking by up to 60%. A Random Forest machine learning model predicts mass loading with high accuracy (+/- 0.3 mg cm(-)2) using surface temperature data, highlighting the feasibility of thermal imaging-based quality estimation. While validated in a batch process, this approach is well-suited for integration into roll-to-roll production across diverse thin coating applications, such as batteries, solar cells, and functional films. Thermal imaging provides a robust pathway for real-time defect detection, drying optimization, and quality control, improving coating performance and production reliability.

关键词： battery electrode defect detection drying dynamics non-destructive testing quality control tool silicon-based thin coatings thermal imaging

来源：评论

学校读者我要写书评

暂无评论

Semantic Mining and Domain Correction Network for Online defect detection of Photovoltaic Data Streams With Nonstationary Distributions

引用

IEEE SENSORS JOURNAL 2025年第4期25卷 7519-7531页

作者： Wang, Shijie Chen, Haiyong Su, Binyi Wang, Zhaoyang Hebei Univ Technol Sch Artificial Intelligence & Data Sci Tianjin 300130 Peoples R China

The online defect detection for actual photovoltaic (PV) data streams is challenging, as the data stream from multiple production lines are unsupervised and unevenly distributed, while existing static defect detectors cannot adapt to such unsupervised nonstationary PV data stream. In this article, we propose a novel semantic mining and domain correction (SMDC) network, which can aid the static defect detector adapt to nonstationary PV data streams encountered in deployment environments in an online unsupervised manner. In SMDC, we proposes a consistency-based semantic-knowledge mining (CSM) module, which selects reliable low-confidence teacher predictions as pseudo labels for potential defective instances during the self-training process based on the teacher-student architecture, so as to better mine the potential semantic knowledge of unlabeled samples in the nonstationary data stream. Then, we introduce a domain correction contrastive learning (DCCL) module, which performs contrastive learning to measure and narrow the distance between defect-free features of test samples and prepreserved background prototypes in the feature space, thereby helping detector to learn robust domain-invariant background feature representations. Finally, extensive experiments based on the public PV dataset demonstrate that the proposed SMDC achieves the state-of-the-art performance for the online defect detection task of the nonstationary PV data stream, which is crucial for the continuous quality monitoring of PV products.

关键词： Streams defect detection Feature extraction Detectors Production Semantics Photovoltaic systems Adaptation models Data models Data mining Nonstationary data stream online learning photovoltaic (PV) defect detection test-time adaptation (TTA)

来源：评论

学校读者我要写书评

暂无评论

Data acquisition system for OLED defect detection and augmentation of system data through diffusion model

引用

JOURNAL OF INFORMATION DISPLAY 2025年第1期26卷 57-63页

作者： Kim, Byungjoon Seo, Yongduek Sogang Univ Dept Art & Technol Media Technol Seoul South Korea Sogang Univ Loyola Int Coll Dept Global Korean Studies Seoul South Korea

This paper presents a system and model for data acquisition and augmentation in OLED panel defect detection to improve detection efficiency. It addresses the challenges of data scarcity, data acquisition difficulties, and classification of different defect types. The proposed system acquires a hypothetical base dataset and employs an image generation model for data augmentation. While image generation models have been instrumental in overcoming data scarcity, time and cost constraints in various fields, they still pose limitations in generating images with regular patterns and detecting defects within such data. Even when datasets are available, the precise definition and classification of different defect types becomes imperative. In this paper, we investigate the feasibility of using an image generation model to generate pattern images for OLED panel defect detection and apply it for data augmentation. In addition, we introduce an OLED panel defect data acquisition system, improve the limitations of data augmentation, and address the challenges of defect detection data augmentation using image generation models.

关键词： Data acquisition data augmentation defect detection OLED defects diffusion model

来源：评论

学校读者我要写书评

暂无评论

Surface defect detection of planar optical components based on OPT-YOLO

引用

OPTICS AND LASERS IN ENGINEERING 2025年 190卷

作者： Huang, Junpeng Zhang, Wang Jin, Weilong Hu, Hongchuan Jilin Univ Sch Mech & Aerosp Engn Changchun 130025 Peoples R China

Surface defects on optical components significantly impact imaging quality, durability, and reliability. Traditional optical and manual detection methods are inefficient and lack accuracy. Therefore, making machine vision is a crucial advancement for surface defect detection. In this article, an imaging system was constructed to generate a proprietary dataset of self-made optical component surface defects and an innovative OPT-YOLO algorithm was developed for detecting surface defects in planar optical components. The RepViTSEBlock and EMA modules were integrated with the C2f backbone network in OPT-YOLO, streamlining weights and enhancing feature extraction. To improve model expression, the MPCA attention mechanism was incorporated into the tail of backbone. Addressing background interference on defect features, ODConv was introduced into the Neck structure, replacing the Bottleneck configuration in C2f. The dysample module is also applied to refine the initial upsample structure to compensate for the problem of upsample easily losing low-level details and semantic information. For more efficient and accurate detection, SCDH detection head was adopted and CIoU was replaced with powerful-IoU, this lightweight structure accelerates convergence and improves anchor box accuracy. Finally, experimental results demonstrate that OPT-YOLO achieves mAP, Precision, and Recall scores of 0.970, 0.979, and 0.920, respectively, marking improvements of 3.2 %, 7.4 %, and 8.7 % over YOLOv8, while reducing FLOPs by 3.6 G, FPS has increased by 94. The heat map and feature map extractions confirm enhanced feature extraction capabilities, and ablation studies validate the performance gains from our enhanced modules. Overall, OPT-YOLO offers a more efficient and precise solution for planar optical component surface defect detection, highlighting its potential for industrial applications.

关键词： OPT-YOLO Optical element Lightweight structure defect detection Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Fully Automatic and Precisely Woven Fabric defect detection Using Improved YOLOv7-Tiny Model Utilizing Enhanced Residual Convolutional Network

引用

FIBERS AND POLYMERS 2025年第1期26卷 353-368页

作者： Barman, Jagadish Kuo, Chung-Feng Jeffrey Natl Taiwan Univ Sci & Technol Dept Mat Sci & Engn Taipei 106 Taiwan

The field of fabric defect detection has undergone a transformative journey marked by the evolution of object detection models. From traditional approaches to advanced deep learning architectures, these models have addressed crucial challenges in the textile industry. YOLOv7-tiny model stands out as a remarkable solution, demonstrating unprecedented performance in fabric defect detection. Its enhanced architecture addresses key industry issues, including high-resolution images, small defect sizes, and imbalanced datasets. Therefore, the aim of this paper is to incorporate the YOLOv7 model with improvements to detect woven fabric defects in real time. Augmenting the Enhanced Residual Convolutional Network (ERCN) with extra Convolutional, batch normalization and leaky rectified linear unit (CBL) layers enhances hierarchical feature extraction, while the two-concatenation technique adds complexity for richer representations. Reducing CBL layers in Efficient layer aggregation networks-downgrade (ELAN-D) streamlines and optimizes, emphasizing a balanced approach in the YOLOv7-tiny model for targeted objectives. The improved YOLOv7-tiny model excels in achieving a delicate balance between accuracy and efficiency, vital for practical applications in the textile sector. This model's accuracy, with a mAP of 84% at a 0.50 threshold and 40% at 0.50:0.95 showed exceptional in comparisons to other models. The model also boasts a high accuracy of 98% and operates at a commendable detection speed of 90 fps, meeting real-time demands in fabric production. Recognizing defects as small as 1 mm, the YOLOv7-tiny model emerges as a pivotal tool in automating fabric defect detection and optimizing textile quality management processes.

关键词： Object detection Real-time Fabric inspection Artificial intelligent defect detection

来源：评论

学校读者我要写书评

暂无评论

Improved RT-DETR Network for High-Quality defect detection on Digital Printing Fabric

引用

JOURNAL OF NATURAL FIBERS 2025年第1期22卷

作者： Su, Zebin Shao, Yunlong Li, Pengfei Zhang, Xingyi Zhang, Huanhuan Xian Polytech Univ Sch Elect & Informat 19 Jinhua South Rd Xian Peoples R China Xian Polytech Univ Shaanxi Artificial Intelligence Joint Lab Xian Peoples R China

Digital printing technology has been successfully implemented in actual production within factories. However, issues with various digital printing heads can still lead to defects in printed fabrics, reducing the pass rate of digital printing textiles. To promptly detect these printing defects, we have constructed a dataset of fabric defects caused by digital printing head malfunctions and propose a high-quality digital printing defect detection model tailored to our self-built dataset. Our model is built upon the Real-Time detection Transformer (RT-DETR) framework, with an added detection head designed for detailed processing in complex backgrounds. We also incorporated an inverted residual mobile block (iRMB) to integrate attention mechanisms into the network's feature extraction process, and improved the bounding box loss function to enhance the model's detection accuracy. Experimental results demonstrate that our model achieves state-of-the-art accuracy on the COCO metrics, with a detection accuracy of 0.588 on the AP index, compared to other advanced detection models. This method effectively identifies fabric defects caused by nozzle failures in digital printing equipment, offering a novel solution for fabric defect detection. (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic). (sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic). (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic), (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic). (sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(sic)(RT-DETR)(sic)(sic)(sic)(sic), (sic)(sic)(sic

关键词： Digital printing defect detection Real-Time detection Transformer (RT-DETR) detection head Inverted residual mobile block (iRMB) bounding box loss (sic)(sic)(sic)(sic) (sic)(sic)(sic)(sic) (sic)(sic)(sic)(sic)(sic)(sic)(sic)(RT-DETR) (sic)(sic)(sic) (sic)(sic)(sic)(sic)(sic)(sic)(sic)(iRMB) (sic)(sic)(sic)(sic)(sic)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：