• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于改进的注意力机制和特征融合模型的表面缺陷检测方法。

Surface Defect Detection Method Based on Improved Attention Mechanism and Feature Fusion Model.

机构信息

School of Electromechanical Engineering, Guangdong University of Technology, Guangzhou, Guangdong 510006, China.

出版信息

Comput Intell Neurosci. 2022 Mar 3;2022:3188645. doi: 10.1155/2022/3188645. eCollection 2022.

DOI:10.1155/2022/3188645
PMID:35281189
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8913145/
Abstract

Cylinder liners are important to automobile engines. The appearance quality will directly affect the life and safety of the engines. At present, the appearance quality inspection of cylinder liners mainly relies on manual visual judgment, which is easily affected by the subjective factors of inspectors. This paper studies improved machine vision to realize surface defect detection. It proposes the improvement of the attention mechanism and a feature fusion method to locate and classify the defect. Experiments show that the method proposed in this paper has improved both accuracy and speed, and it can detect defects in production and realize industrialization. At the same time, the method studied in this paper has the value of popularization and application for appearance defect detection in other fields.

摘要

缸套对汽车发动机至关重要。其外观质量将直接影响发动机的寿命和安全性。目前，缸套的外观质量检测主要依靠人工目视判断，容易受到检验员主观因素的影响。本文研究了改进的机器视觉，以实现表面缺陷检测。提出了改进的注意力机制和特征融合方法，用于定位和分类缺陷。实验表明，本文提出的方法提高了准确性和速度，可以在生产中检测缺陷，实现工业化。同时，本文研究的方法对于其他领域的外观缺陷检测具有推广应用价值。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/95a0d42daed6/CIN2022-3188645.019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/da8561a24957/CIN2022-3188645.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/ee2d3900c23a/CIN2022-3188645.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/4da15873f4b6/CIN2022-3188645.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/bec024bf21a9/CIN2022-3188645.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/c5b3a2ef821a/CIN2022-3188645.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/ee0b5f9ac256/CIN2022-3188645.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/b4f0343a3c92/CIN2022-3188645.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/bfa250ae783d/CIN2022-3188645.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/9a4a3f770009/CIN2022-3188645.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/4e578f8f7d06/CIN2022-3188645.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/0dbd2c2a19e9/CIN2022-3188645.011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/cf0f69c8c6c1/CIN2022-3188645.012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/9e5f2cd08de7/CIN2022-3188645.013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/985946a790a4/CIN2022-3188645.014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/70af4abefc6b/CIN2022-3188645.015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/603df3229a6f/CIN2022-3188645.016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/158a4d3ca89e/CIN2022-3188645.017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/1183afbc7ecf/CIN2022-3188645.018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/95a0d42daed6/CIN2022-3188645.019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/da8561a24957/CIN2022-3188645.001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/ee2d3900c23a/CIN2022-3188645.002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/4da15873f4b6/CIN2022-3188645.003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/bec024bf21a9/CIN2022-3188645.004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/c5b3a2ef821a/CIN2022-3188645.005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/ee0b5f9ac256/CIN2022-3188645.006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/b4f0343a3c92/CIN2022-3188645.007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/bfa250ae783d/CIN2022-3188645.008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/9a4a3f770009/CIN2022-3188645.009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/4e578f8f7d06/CIN2022-3188645.010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/0dbd2c2a19e9/CIN2022-3188645.011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/cf0f69c8c6c1/CIN2022-3188645.012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/9e5f2cd08de7/CIN2022-3188645.013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/985946a790a4/CIN2022-3188645.014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/70af4abefc6b/CIN2022-3188645.015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/603df3229a6f/CIN2022-3188645.016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/158a4d3ca89e/CIN2022-3188645.017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/1183afbc7ecf/CIN2022-3188645.018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/82dc/8913145/95a0d42daed6/CIN2022-3188645.019.jpg

相似文献

1
Surface Defect Detection Method Based on Improved Attention Mechanism and Feature Fusion Model.基于改进的注意力机制和特征融合模型的表面缺陷检测方法。
Comput Intell Neurosci. 2022 Mar 3;2022:3188645. doi: 10.1155/2022/3188645. eCollection 2022.
2
Industrial cylinder liner defect detection using a transformer with a block division and mask mechanism.使用具有块划分和掩码机制的变压器进行工业气缸套缺陷检测。
Sci Rep. 2022 Jun 23;12(1):10689. doi: 10.1038/s41598-022-14971-8.
3
A full-flow inspection method based on machine vision to detect wafer surface defects.一种基于机器视觉的全流程检测方法，用于检测晶圆表面缺陷。
Math Biosci Eng. 2023 May 9;20(7):11821-11846. doi: 10.3934/mbe.2023526.
4
Track Fastener Defect Detection Model Based on Improved YOLOv5s.基于改进YOLOv5s的轨道扣件缺陷检测模型
Sensors (Basel). 2023 Jul 17;23(14):6457. doi: 10.3390/s23146457.
5
An Automatic Surface Defect Inspection System for Automobiles Using Machine Vision Methods.基于机器视觉的汽车表面自动缺陷检测系统。
Sensors (Basel). 2019 Feb 4;19(3):644. doi: 10.3390/s19030644.
6
Real-time batch inspection system for surface defects on circular optical filters.圆形光学滤光片表面缺陷实时批量检测系统
Appl Opt. 2022 Nov 10;61(32):9634-9645. doi: 10.1364/AO.474272.
7
An Efficient YOLO Algorithm with an Attention Mechanism for Vision-Based Defect Inspection Deployed on FPGA.一种基于注意力机制的高效YOLO算法，用于基于视觉的缺陷检测并部署在FPGA上。
Micromachines (Basel). 2022 Jun 30;13(7):1058. doi: 10.3390/mi13071058.
8
Multilayer Feature Extraction of AGCN on Surface Defect Detection of Steel Plates.基于AGCN的钢板表面缺陷检测的多层特征提取
Comput Intell Neurosci. 2022 Oct 3;2022:2549683. doi: 10.1155/2022/2549683. eCollection 2022.
9
A visual defect detection for optics lens based on the YOLOv5 -C3CA-SPPF network model.基于 YOLOv5-C3CA-SPPF 网络模型的光学镜头视觉缺陷检测。
Opt Express. 2023 Jan 16;31(2):2628-2643. doi: 10.1364/OE.480816.
10
Steel Wire Rope Surface Defect Detection Based on Segmentation Template and Spatiotemporal Gray Sample Set.基于分割模板和时空灰度样本集的钢丝绳表面缺陷检测
Sensors (Basel). 2021 Aug 10;21(16):5401. doi: 10.3390/s21165401.

引用本文的文献

1
Retracted: Surface Defect Detection Method Based on Improved Attention Mechanism and Feature Fusion Model.撤回：基于改进注意力机制和特征融合模型的表面缺陷检测方法。
Comput Intell Neurosci. 2023 Aug 2;2023:9827489. doi: 10.1155/2023/9827489. eCollection 2023.
2
A Domestic Trash Detection Model Based on Improved YOLOX.基于改进 YOLOX 的家庭垃圾检测模型。
Sensors (Basel). 2022 Sep 15;22(18):6974. doi: 10.3390/s22186974.

本文引用的文献

1
Automatic detection and classification of manufacturing defects in metal boxes using deep neural networks.基于深度神经网络的金属盒制造缺陷自动检测与分类
PLoS One. 2018 Nov 9;13(11):e0203192. doi: 10.1371/journal.pone.0203192. eCollection 2018.