检索结果-南通市图书馆

Global fabric defect detection Based on Unsupervised Characterization

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2021年第2期26卷 231-238页

作者： WU Ying LOU Lin WANG Jun Clothing Engineering Research Center of Zhejiang Province School of Fashion Design and EngineeringZhejiang Sci-Tech UniversityHangzhou 310018China Key Laboratory of Textile Science and Technology of Ministry of Education College of TextilesDonghua UniversityShanghai 201620China

fabric texture intelligent analysis comprises the following characteristics:objective detection results,high detection efficiency,and *** is significantly vital to replace manual inspection for smart green manufacturing in the textile industry,such as quality control and rating,and online *** detecting the global image,an unsupervised method is proposed to characterize the woven fabric texture image,which is the combination of principal component analysis(PCA)and dictionary *** of all,the PCA approach is used to reduce the dimension of fabric samples,the obtained eigenvector is used as the initial dictionary,and then the dictionary learning method is operated on the defect-free region to get the standard ***,the standard templates are optimized by choosing the appropriate dictionary size to construct a fabric texture representat ion model that can effectively characterize the defec-free texture region,while ineffectively representing the defective *** is to say,through the mechanism of identifying normal texture from imperfect texture,a learned dictionary with robustness and discrimination is obtained to adapt the fabric ***,after matching the detected image with the standard templates,the average filter is used to remove the noise and suppress the background texture,while retaining and enhancing the defect *** the final part,the image segmentation is operated to identify the *** experimental results show that the proposed algorithm can adequately inspect fabrics with defects such as holes,oil stains,skipping,other defective types,and non-defective materials,while the detection results are good and the algorithrm can be operated flexibly.

关键词： fabric defect detection unsupervised characterization fabric texture learned dictionary

Semantic Segmentation Using DeepLabv3+ Model for fabric defect detection

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Wuhan University Journal of Natural Sciences 2022年第6期27卷 539-549页

作者： ZHU Runhu XIN Binjie DENG Na FAN Mingzhu School of Electronic and Electrical Engineering Shanghai University of Engineering ScienceShanghai 201620China School of Textile and Fashion Technology Shanghai University of Engineering ScienceShanghai 201620China

Currently, numerous automatic fabric defect detection algorithms have been proposed. Traditional machine vision algorithms that set separate parameters for different textures and defects rely on the manual design of corresponding features to complete the detection. To overcome the limitations of traditional algorithms, deep learning-based correlative algorithms can extract more complex image features and perform better in image classification and object detection. A pixel-level defect segmentation methodology using DeepLabv3+, a classical semantic segmentation network, is proposed in this paper. Based on ResNet-18,ResNet-50 and Mobilenetv2, three DeepLabv3+ networks are constructed, which are trained and tested from data sets produced by capturing or publicizing images. The experimental results show that the performance of three DeepLabv3+ networks is close to one another on the four indicators proposed(Precision, Recall, F1-score and Accuracy), proving them to achieve defect detection and semantic segmentation, which provide new ideas and technical support for fabric defect detection.

关键词： fabric defect detection semantic segmentation deep learning DeepLabv3+

Review of fabric defect detection Based on Computer Vision

在线全文

学校读者我要写书评

暂无评论

Journal of Donghua University(English Edition) 2023年第1期40卷 18-26页

作者：朱润虎辛斌杰邓娜范明珠 School of Electronic and Electrical Engineering Shanghai University of Engineering ScienceShanghai 201620China School of Textiles and Fashion Shanghai University of Engineering ScienceShanghai 201620China

In textile inspection field,the fabric defect refers to the destruction of the texture structure on the fabric *** technology of computer vision makes it possible to detect defects ***,the overall structure of the fabric defect detection system is introduced and some mature detection systems are *** the fabric detection methods are summarized,including structural methods,statistical methods,frequency domain methods,model methods and deep learning *** addition,the evaluation criteria of automatic detection algorithms are discussed and the characteristics of various algorithms are ***,the research status of this field is discussed,and the future development trend is predicted.

关键词： computer vision fabric defect detection algorithm evaluation textile inspection

同方期刊数据库

Multi-Layer Feature Extraction with Deformable Convolution for fabric defect detection

在线全文

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2024年第4期39卷 725-744页

作者： Jielin Jiang Chao Cui Xiaolong Xu Yan Cui School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China State Key Lab.for Novel Software Technology Nanjing UniversityNanjing210023China Engineering Research Center of Digital Forensics Ministry of EducationNanjing University of Information Science and TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science and TechnologyNanjing210044China College of Mathematics and Information Science Nanjing Normal University of Special EducationNanjing210038China

In the textile industry,the presence of defects on the surface of fabric is an essential factor in determining fabric ***,identifying fabric defects forms a crucial part of the fabric production *** fabric defect detection algorithms can only detect specific materials and specific fabric defect types;in addition,their detection efficiency is low,and their detection results are relatively *** learning-based methods have many advantages in the field of fabric defect detection,however,such methods are less effective in identifying multiscale fabric defects and defects with complex ***,we propose an effective algorithm,namely multilayer feature extraction combined with deformable convolution(MFDC),for fabric defect *** MFDC,multi-layer feature extraction is used to fuse the underlying location features with high-level classification features through a horizontally connected top-down architecture to improve the detection of multi-scale fabric *** this basis,a deformable convolution is added to solve the problem of the algorithm’s weak detection ability of irregularly shaped fabric *** this approach,Roi Align and Cascade-RCNN are integrated to enhance the adaptability of the algorithm in materials with complex patterned *** experimental results show that the MFDC algorithm can achieve good detection results for both multi-scale fabric defects and defects with complex shapes,at the expense of a small increase in detection time.

关键词： fabric defect detection multi-layer features deformable convolution

An Enhanced Nonlocal Self-Similarity Technique for fabric defect detection

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Information Hiding and Privacy Protection 2019年第3期1卷 135-142页

作者： Boheng Wang Li Ma Jielin Jiang School of Computer&Software Nanjing University of Information Science&TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science&Technology Nanjing210044China

fabric defect detection has been an indispensable and important link in fabric production,many studies on the development of vision based automated inspection techniques have been *** main drawback of existing methods is that they can only inspect a particular type of fabric pattern in controlled ***,nonlocal self-similarity(NSS)based method is used for fabric defect *** method achieves good defect detection performance for small defects with uneven illumination,the disadvantage of NNS based method is poor for detecting linear *** on this reason,we improve NSS based defect detection method by introducing a gray density function,namely an enhanced NSS(ENSS)based defect detection ***,mean filter is applied to smooth images and suppress *** results prove the validity and feasibility of the proposed NLRA algorithm.

关键词： fabric defect detection nonlocal self-similarity mean filter

detection of fabric defects with Fuzzy Label Co-occurrence Matrix Set

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Donghua University(English Edition) 2009年第5期26卷 549-553页

作者：邹超汪秉文孙志刚 Department of Control Science and Engineering Huazhong University of Science and Technology

Co-occurrence matrices have been successfully applied in texture classification and ***,they have poor computation performance in real-time *** this paper,the efficient co-occurrence matrix solution for defect detection is focused on,and a method of Fuzzy Label Co-occurrence Matrix (FLCM) set is *** this method,all gray levels are supposed to subject to some fuzzy sets called fuzzy tonal sets and three defective features are *** of FLCM set with various parameters are combined for the final *** many methods,image acquired for learning hasn't to be entirely free of *** is shown that the method produces high accuracy and can be a competent candidate for plain colour fabric defect detection.

关键词： fabric defect detection fuzzy label cooccurrence matrix set fuzzy logic

Automatic Image Inspection of fabric defects Based on Optimal Gabor Filter

在线全文

学校读者我要写书评

暂无评论

Journal of Donghua University(English Edition) 2016年第4期33卷 545-548页

作者：尉苗苗李岳阳蒋高明丛洪莲 Engineering Research Center for Knitting Technology Ministry of EducationJiangnan University

An effective method for automatic image inspection of fabric defects is presented. The proposed method relies on a tuned 2D-Gabor filter and quantum-behaved particle swarm optimization( QPSO) algorithm. The proposed method consists of two main steps:( 1) training and( 2) image inspection. In the image training process,the parameters of the 2D-Gabor filters can be tuned by QPSO algorithm to match with the texture features of a defect-free template. In the inspection process, each sample image under inspection is convoluted with the selected optimized Gabor *** a simple thresholding scheme is applied to generating a binary segmented result. The performance of the proposed scheme is evaluated by using a standard fabric defects database from Cotton Incorporated. Good experimental results demonstrate the efficiency of proposed method. To further evaluate the performance of the proposed method,a real time test is performed based on an on-line defect detection system. The real time test results further demonstrate the effectiveness, stability and robustness of the proposed method,which is suitable for industrial production.

关键词： fabric defect detection optimal Gabor filter quantum-behaved particle swarm optimization(QPSO) algorithm image segmentation

一种基于深度学习的轻量级牛仔布缺陷检测方法

在线全文

学校读者我要写书评

暂无评论

一种基于深度学习的轻量级牛仔布缺陷检测方法

作者： Dang Van Minh 华南理工大学

学位级别：硕士

This thesis proposes “Denim-YOLO”,an efficient deep learning model tailored for the real-time detection of defects in denim fabric ***-YOLO is developed upon the computationally efficient foundation of YOLOv8 *** then integrated novel elements that enhance detection accuracy without significantly increasing the computational *** model has been rigorously validated on our Denim fabric dataset,which is carefully collected to mimic real-world manufacturing conditions,ensuring its practical applicability in industrial settings.From the baseline,we conducted multiple experiments including variations in loss functions,activation functions,and trials of different attention and transformer *** experiments provide valuable insights into the effects of each element on an object detection model,aiding in a deeper understanding of how a model behaves under various architectural modifications.The Denim-YOLO model employs a suite of advanced techniques over the baseline YOLOv8 n model: CARAFE operation for efficient feature map upsampling,Ghost convolution to reduce computational complexity while preserving performance,deformable convolution to improve receptive fields and enhance robustness against noise and spatial ***,shuffle attention,a lightweight and hybrid attention mechanism,is utilized to enhance model's ability to extract complex features and small *** Uv3 is employed as bounding box regression loss to enhance convergence speed during tranining and prediction accuracy,and softplus activation is selected empirically to further augment model *** ablation studies offer a thorough evalution at each component's contribution to the model's performance,emphasising our methodological approach to model development.In performance comparision,Denim-YOLO outperforms the baseline YOLOv8 n with m AP50 of 0.917 and m AP50-95 score of 0.574,marking improvements of 3.7% and 0.6%respectively.M

关键词： fabric defect detection deep learning object detection YOLOv8 Attention mechanism Grad-Cam

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

基于YOLOv7的织物缺陷检测

基于YOLOv7的织物缺陷检测

作者： Salman Shehzad 华南理工大学

学位级别：硕士

Object detection is the documentation of an object in the image laterally with its localization and *** has inclusive range applications and critical component for vision-based software *** fabric defect detection is a challenging problem in machine learning with wide application field.A requirement for realization of a machine defect picker is its ability to detect defect in the *** expert system,which would be able to compete with human perception,must be skillful of recognizing defect among the fabric and textile under uncontrolled conditions,where fabric are occluded and *** the other hand,the localization accuracy can easily be detect defect in the textiles *** and classify defect picking points plays a vital role in machine *** defect is detected in images using YOLOv7 to detect defect in fabrics and a state-of-the-art *** adopt this model,through fine-tuning,for the task of fabric defect based *** main objective of current research is to design an efficient and accurate YOLOV7 Model based on fabric defect *** test results show the proposed algorithm has achieved higher detection accuracy and lower processing time than the traditional *** work demonstrated that we introduce a new,high-quality dataset of images containing fabric *** work presents diferent YOLOv7 models channel attention mechanisms like CA,SE,ECA and replace the loss function from the CIo U to EIo *** model based on YOLOv7 and channel attention mechanism and comparative analysis of test result with based model and define loss function after conducting the multiples experiments the result of the improved model reached the mean average Precision m AP upto 99.40%This research based on fabric defect detection using DAGM dataset containing above from the 18000 images having ten multiple *** first the discussion about the YOLO family and improvement of each version of YOLO an

关键词： fabric defect detection YOLOv7 CA SE EIoU CNN Pytorch Inceptionv2