检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing (ICIP)

作者： Lin, Dongyun Li, Yiqun Prasad, Shitala Nwe, Tin Lay Dong, Sheng Oo, Zaw Min Inst Infocomm Res I2R Singapore 138632 Singapore

ISBN: (纸本)9781665441155

defect segmentation is critical in real-wold industrial product quality assessment. There are usually a huge number of normal (defect-free) images but a very limited number of annotated anomalous images. This poses huge challenges to exploiting Fully-Convolutional Networks (FCN), e.g., UNet, as they require sufficient anomalous images with defect annotations during training. To further leverage the information from normal data, a novel CAM-guided U-Net with adversarial regularization (CAM-UNet-AR) is proposed. We first modify the existing CAM-UNet to incorporate the CAMs for both normal and anomalous classes and fine-tune the segmentation network using a combined loss which jointly considers pixel-wise classification, foreground segmentation and boundary segmentation. Secondly, an auxiliary adversarial regularization module (ARM) is proposed to facilitate the segmentation network to encode the "normal components" from training images into consistent representations. Extensive experiments on MVTec AD dataset show the superiority of our proposed network over multiple state-of-the-art U-Net variants.

关键词： defect segmentation U-Net Adversarial Regularization

来源：评论

学校读者我要写书评

暂无评论

MLSA-UNET: END-TO-END MULTI-LEVEL SPATIAL ATTENTION GUIDED UNET FOR INDUSTRIAL defect segmentation 29

MLSA-UNET: END-TO-END MULTI-LEVEL SPATIAL ATTENTION GUIDED U...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Lin, Dongyun Cheng, Yi Li, Yiqun Prasad, Shitala Guo, Aiyuan Inst Infocomm Res I2R Singapore 138632 Singapore

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

defect segmentation from 2D images plays a critical role in industrial product quality assessment. In practice, it is common that there are sufficient normal (defect-free) images but a very limited number of anomalous (defective) images. The existing works proposed several UNet variants (e.g., CAM-UNet) by incorporating normal images into the training process to improve the defect segmentation performance. In this paper, we propose Multi-Level Spatial Attention UNet (MLSA-UNet) to address the industrial defect segmentation task. MLSA-UNet is trained in an end-toend manner to simultaneously classify normal/anomalous images and segment out defective regions from anomalous images. The classification process is conducted by Spatial Attention Learning Module (SALM) to generate multi-level spatial attention maps which are exploited by Spatial Attention Guided Decoding Module (SADM) to provide the guidance in the decoding process of UNet. Extensive experiments on MVTec AD dataset demonstrate the superiority of the proposed MLSA-UNet over multiple state-of-the-art UNet variants on defect segmentation.

关键词： defect segmentation UNet Multi-Level Spatial Attention

来源：评论

学校读者我要写书评

暂无评论

A generic deep-learning based defect segmentation model for electron micrographs for automatic defect inspection 37

A generic deep-learning based defect segmentation model for ...

引用

Conference on Metrology, Inspection, and Process Control XXXVII

作者： Jacob, Martin Hallal, Ali Baderot, Julien Barra, Vincent Guillin, Arnaud Martinez, Sergio Foucher, Johann POLLEN Metrol Novespace A 122 Rue Rocher de Lorzier F-38430 Moirans France Univ Clermont Auvergne CNRS Mines St Etienne Clermont Auvergne INPLIMOS F-63000 Clermont Ferrand France Univ Clermont Auvergne Lab Math Blaise Pascal UMR 6620 Aubiere France Inst Univ France Paris France

ISBN: (纸本)9781510660991;9781510661004

defect inspection is an important part in the semiconductor manufacturing. This task is tedious and time consuming if done manually. Therefore, reliably automating this task is a major challenge for many semiconductor manufacturers. In the recent years, deep-learning methods for object detection have demonstrated ever better performances. However, most of the publicly available models are trained on natural images and objects. Hence, most of them needs a long and data greedy training step to be used on industrial Transmission Electron Microscopes or Scanning Electron Microscope images. In this context, we propose a deep-learning based model to detect and segment defects in electron micrographs. Using SmartDef3 from Pollen Metrology, we annotated defects on images from several industrial applications. We split them in a training and validation dataset, with which an Instance segmentation model with state-of-the-art backbone is trained. The model is then evaluated on different use cases. Competitive performances on new data in terms of detection rates and segmentation quality are demonstrated and discussed. Furthermore, the model showed a relevant defect detection rate even on images that are not in the semiconductor domain, providing an interesting tool for defects detection on a new use case without new training data. This shows how deep learning strategies can help save time and costs by automation of defects inspections. Furthermore, advanced metrological analysis of the defect can be simultaneously obtained that help optimizing the manufacturing processes and reduce defect production rate.

关键词： Deep learning defect inspection defect segmentation

来源：评论

学校读者我要写书评

暂无评论

Improving Unsupervised defect segmentation by Applying Structural Similarity to Autoencoders 14

Improving Unsupervised Defect Segmentation by Applying Struc...

引用

14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP)

作者： Bergmann, Paul Loewe, Sindy Fauser, Michael Sattlegger, David Steger, Carsten MVTec Software GmbH Munich Germany Univ Amsterdam Amsterdam Netherlands

ISBN: (纸本)9789897583544

Convolutional autoencoders have emerged as popular methods for unsupervised defect segmentation on image data. Most commonly, this task is performed by thresholding a per-pixel reconstruction error based on an `p-distance. This procedure, however, leads to large residuals whenever the reconstruction includes slight localization inaccuracies around edges. It also fails to reveal defective regions that have been visually altered when intensity values stay roughly consistent. We show that these problems prevent these approaches from being applied to complex real-world scenarios and that they cannot be easily avoided by employing more elaborate architectures such as variational or feature matching autoencoders. We propose to use a perceptual loss function based on structural similarity that examines inter-dependencies between local image regions, taking into account luminance, contrast, and structural information, instead of simply comparing single pixel values. It achieves significant performance gains on a challenging real-world dataset of nanofibrous materials and a novel dataset of two woven fabrics over state-of-the-art approaches for unsupervised defect segmentation that use per-pixel reconstruction error metrics.

关键词： Unsupervised Learning Anomaly Detection defect segmentation

来源：评论

学校读者我要写书评

暂无评论

CAM-UNET: CLASS ACTIVATION MAP GUIDED UNET WITH FEEDBACK REFINEMENT FOR defect segmentation

CAM-UNET: CLASS ACTIVATION MAP GUIDED UNET WITH FEEDBACK REF...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Lin, Dongyun Li, Yiqun Prasad, Shitala Nwe, Tin Lay Dong, Sheng Oo, Zaw Min Inst Infocomm Res I2R Visual Intelligence Dept Adv Mfg Sr Engn Div Singapore 138632 Singapore

ISBN: (纸本)9781728163956

This paper tackles the task of defect segmentation by exploiting sufficient normal (defect-free) training images and limited annotated anomalous images. We propose a class activation map guided UNet (CAM-UNet) with feedback refinement mechanism for accurate defect segmentation. We first modify and pretrain the encoder of a VGG-16 backboned UNet to classify normal and anomalous training images. Then, for each of the anomalous training images, a CAM is generated as the prior segmentation information. Based on the CAM, we propose a feedback refinement process to train two decoder networks to progressively improve the segmentation output. Extensive experiments conducted on MVTEC AD dataset show that the proposed method significantly outperforms multiple benchmarking UNet methods in terms of mean IOU.

关键词： defect segmentation Class Activation Map UNet

来源：评论

学校读者我要写书评

暂无评论

Study of defect segmentation from a Mode Background Image 16

Study of Defect Segmentation from a Mode Background Image

引用

16th IEEE International Conference on Mechatronics and Automation (IEEE ICMA)

作者： Han, Fangfang Xie, Fuhua Zhang, Baofeng Zhu, Junchao Tianjin Univ Technol Tianjin Key Lab Control Theory & Applicat Complic Binshui Xidao 391 Tianjin 300384 Peoples R China Minist Educ Engn Res Ctr Optoelect Devices & Commun Technol Binshui Xidao 391 Tianjin 300384 Peoples R China

ISBN: (纸本)9781728116976

The difficulty of machine vision defect detection is how to extract the defect target from the background image, especially the defect target segmentation under the pattern background image. The pattern background image has more complex pattern, contour, color or texture information, while the defect target and the background area have the same color or grayscale, and it cannot be well segmented with the conventional gray threshold or the tone threshold. This paper focuses on the defect segmentation of pattern background image and discusses the defect segmentation of pattern background image in several cases. The key problem discussed in this paper is how to convert the defect of pattern background image into the contrast defect of non-pattern background image. In this paper, the method of removing transverse and longitudinal texture based on wavelet transform and slant texture based on discrete cosine transform is proposed, and the defect of pattern background image is converted into the contrast defect of non-pattern background image, so as to simplify the segmentation algorithm and improve the segmentation speed. Experiments show that the algorithm proposed in this paper has good segmentation effect for segmentation of defects in horizontal, vertical and oblique texture.

关键词： Machine vision detection defect segmentation Texture removing Wavelet transform Discrete Cosine transform

来源：评论

学校读者我要写书评

暂无评论

Low-contrast X-ray image defect segmentation via a novel core-profile decomposition network

引用

COMPUTERS IN INDUSTRY 2024年 161卷

作者： Liu, Xiaoyuan Liu, Jinhai Zhang, Huanqun Zhang, Huaguang Northeastern Univ Coll Informat Sci & Engn Shenyang 110819 Peoples R China Shenyang Paidelin Technol Co Ltd Shenyang 110081 Peoples R China

Accurate X-ray image defect segmentation is of paramount importance in industrial contexts, as it is the foundation for product quality control and production safety. Deep learning (DL) has demonstrated powerful image scene understanding capabilities and has achieved unprecedented performance in defect segmentation tasks. However, existing DL methods suffer from significant performance degradation when facing low-contrast X-ray images, as the core information of defects is often obscured and the profile details are ambiguous. To address this issue, this paper explicitly decomposes the X-ray defect segmentation task into two subtasks: core feature learning and elasticity profile refinement, allowing task "serial"decomposition and performance "parallel"improvement. On this basis, a novel core-profile decomposition network (CPDNet) is developed to achieve accurate defect segmentation of X-ray images. Specifically, the core feature learning module is designed to construct the effective feature space from two views, discriminative and structural, to extract defect-related core features from X-ray images. Subsequently, the elasticity profile refinement module is developed to further improve the defect segmentation performance, which makes the first attempt to define the profile refinement as an out-of-distribution detection and leverage the elasticity score to refine the profile details at the pixel level. To fully evaluate the presented method, we conduct a series of experiments using two real-world X-ray defect datasets, and the results demonstrate that the CPDNet outperforms state-of-the-art methods.

关键词： defect segmentation Low-contrast X-ray image Core feature Profile refinement Quality control

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware and dynamically-mixed pseudo-labels for semi-supervised defect segmentation

引用

COMPUTERS IN INDUSTRY 2023年第1期152卷

作者： Sime, Dejene M. Wang, Guotai Zeng, Zhi Peng, Bei Univ Elect Sci & Technol China Sch Mech & Elect Engn Chengdu 611731 Sichuan Peoples R China

Deep learning-based defect segmentation is one of the important tasks of machine vision in automated inspection. Supervised learning methods have recently achieved remarkable performance on this task. However, the effectiveness of the supervised methods is limited by the scarcity and high cost of pixel-level annotation of training data. Semi-supervised learning methods have been proposed for training deep learning networks using a limited amount of labeled data along with additional unlabeled data for image segmentation. Most of these methods are based on consistency regularization and pseudo labeling, where the predictions on unlabeled samples often come with noise and are unreliable, resulting in poor segmentation performance. To alleviate this problem, we propose uncertainty-aware pseudo labels, which are generated from dynamically mixed predictions of multiple decoders that leverage a shared encoder network. The estimated uncertainty guides the pseudo-label-based supervision and regularizes the training when using the unlabeled samples. In our experiments on four public datasets for defect segmentation, the proposed method outperformed the fully supervised baseline and six state-of-the-art semi-supervised segmentation methods. We also conducted an extensive ablation study to demonstrate the effectiveness of our approach in various settings. The implementation code for this work is available at https://***/djene-mengistu/UAPS.

关键词： defect segmentation Semi-supervised learning Uncertainty estimation Uncertainty-aware learning Pseudo-label supervision

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Learning for defect segmentation with Autoencoder Auxiliary Module

引用

SENSORS 2022年第8期22卷 2915页

作者： Sae-ang, Bee-ing Kumwilaisak, Wuttipong Kaewtrakulpong, Pakorn King Mongkuts Univ Technol Thonburi Elect & Engn Bangkok 10140 Thailand Tesla Inc Austin TX 78725 USA

In general, one may have access to a handful of labeled normal and defect datasets. Most unlabeled datasets contain normal samples because the defect samples occurred rarely. Thus, the majority of approaches for anomaly detection are formed as unsupervised problems. Most of the previous methods have typically chosen an autoencoder to extract the common characteristics of the unlabeled dataset, assumed as normal characteristics, and determine the unsuccessfully reconstructed area as the defect area in an image. However, we could waste the ground truth data if we leave them unused. In addition, a suitable choice of threshold value is needed for anomaly segmentation. In our study, we propose a semi-supervised setting to make use of both unlabeled and labeled samples and the network is trained to segment out defect regions automatically. We first train an autoencoder network to reconstruct defect-free images from an unlabeled dataset, mostly containing normal samples. Then, a difference map between the input and the reconstructed image is calculated and feeds along with the corresponding input image into the subsequent segmentation module. We share the ground truth for both kinds of input and train the network with binary cross-entropy loss. Additional difference images can also increase stability during training. Finally, we show extensive experimental results to prove that, with help from a handful of ground-truth segmentation maps, the result is improved overall by 3.83%.

关键词： defect segmentation deep learning semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Convolution Residual Network for Heating-Invariant defect segmentation in Composite Materials Inspected by Lock-in Thermography

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2021年 70卷 1页

作者： Morelli, Davide Marani, Roberto D'Accardi, Ester Palumbo, Davide Galietti, Umberto D'Orazio, Tiziana Natl Res Council Italy Inst Intelligent Syst Automat Italian I-70126 Bari Italy Politecn Bari Dept Mech Math & Management I-70125 Bari Italy

This article proposes an automatic approach for segmenting inclusion defects in composite materials inspected by lock-in thermography (LT) in a heat source invariant way. In the proposed pipeline, temperature maps are preliminarily processed to enhance the contrast between sound and defective areas, reduce the acquisition noise, and mitigate the effect of nonuniform heat excitation. Then, the enhanced sequences are grouped in highly local sets, the input of a convolution residual neural network, which segments the defects focusing on the temporal evolution of the temperature. Experiments have been run on a dataset acquired from a CFRP specimen tested under five different heat source configurations. Here, a brief study of signal variations associated with the heat source configuration is presented. Then, an ablation study has been presented to compare different architectures of increasing complexity. The best results are achieved by using the proposed preliminary processing, the residual layers, and an input set of temperature signals of size 3 x 3. This network can reach a global intersection over union (IOU) of 0.78, while defects are segmented with an IOU value of 0.58. In addition, the balanced segmentation accuracy of the test reaches 94.78%, with a maximum recall of the defective class of 91.41%. Further cross validation changing the source configurations of the training and test sets produces comparable results of IOU and balanced accuracy, which are on average equal to 0.71 and 84.02%, respectively. A final evaluation of the trained network is performed on a new dataset augmented through a vertical stretch. Results are still comparable with an average IOU and balanced accuracy of 0.74 and 87.15%, respectively. These results prove the capability of the method to segment inclusion defects of any shape without being affected by the configuration of the heating sources used in the LT inspections.

关键词： Computer vision deep learning defect segmentation infrared (IR) thermography neural network (NN) time-based analysis

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：