Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Direct Tissue Mass Spectrometry Imaging by Atmospheric Pressure UV-Laser Desorption Plasma Postionization.

Journal of the American Society for Mass Spectrometry·2020
Same author

A novel secretagogin/ATF4 pathway is involved in oxidized LDL-induced endoplasmic reticulum stress and islet β-cell apoptosis.

Acta biochimica et biophysica Sinica·2020
Same author

Intravenous Thrombolysis before Thrombectomy may Increase the Incidence of Intracranial Hemorrhage inTreating Carotid T Occlusion.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2020
Same author

Safety and efficacy of traditional Chinese medicine, Qiaoshao formula, combined with dapoxetine in the treatment of premature ejaculation: An open-label, real-life, retrospective multicentre study in Chinese men.

Andrologia·2020
Same author

New insights into the interplay between miRNAs and autophagy in the aging of intervertebral discs.

Ageing research reviews·2020
Same author

Characterization of a Plasmid-Encoded Resistance-Nodulation-Division Efflux Pump in <i>Klebsiella pneumoniae</i> and <i>Klebsiella quasipneumoniae</i> from Patients in China.

Antimicrobial agents and chemotherapy·2020

相关实验视频

Updated: May 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K

基于边界注意力引导微调的PCB CT图像元件细分模型.

Chen Chen1, Kai Qiao1, Jie Yang1

  • 1School of Information Systems Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, Henan, China.

Journal of X-ray science and technology
|February 20, 2025
PubMed
概括

本研究引入了一种新的边界注意引导微调模型,用于在计算机断层扫描 (CT) 图像中对印刷电路板 (PCB) 元素进行细分,提高精度和特征融合效率.

科学领域:

  • 计算机视觉 计算机视觉
  • 非破坏性测试 不破坏性测试
  • 图像细分 图像细分

背景情况:

  • 计算机断层扫描 (CT) 对于印刷电路板 (PCB) 的非破坏性测试至关重要.
  • 由于灰度不一致性和层透,PCBCT图像中的元素细分具有挑战性,导致边界不准确.
  • 现有的预训练和微调方法与这些图像工件作斗争,影响语义理解.

研究的目的:

  • 为了解决PCBCT图像元件分段的局限性,特别是边界定义差.
  • 提高PCBCT分析中元素分割的准确性和可靠性.

主要方法:

  • 针对PCB CT图像元件细分,提出了一种新的边界注意引导微调模型 (BAG-FTseg).
  • 一个改进的边界检测算法增强了模型感知元素边界的能力.
  • 一个注意力特征融合模块有效地集成边界特征,使用注意力机制来改善细分.

主要成果:

  • 拟议的BAG-FTseg模型在PCB CT数据集上实现了89.5%的欧盟交叉点 (mIoU) 的平均值.
  • 该模型显示,与基线模型相比,整体mIoU的改善率为0.9%.
  • 边界特定的mIoU达到69.5%,比基线显著增加5.3%,突出显示了改善的边界细分.
关键词:
对PCB进行非破坏性测试.边界感知知觉的边界面具图像建模 面具图像建模语义细分 语义细分 语义细分 语义细分

更多相关视频

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images
09:21

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

12.1K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

454

相关实验视频

Last Updated: May 27, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images
09:21

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

12.1K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

454

结论:

  • 开发的方法提高了PCB元素边界细分的准确性.
  • 注意力机制提高了特征融合效率,有助于PCB分析的实际进展.
  • 这种方法为PCB的非破坏性测试和质量控制提供了显著的实际价值.