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

Detection of Gross Error: The Q Test01:00

Detection of Gross Error: The Q Test

When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...

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

Hormesis induced by lithium exposures influenced the effects of maternal age at reproduction on offspring quality of Brachionus calyciflorus: A multigenerational study.

Aquatic toxicology (Amsterdam, Netherlands)·2026
Same author

Development of Peroxymonosulfate Catalytic System and Photoenzymatic Catalytic System Utilizing Zn-Doped g-C<sub>3</sub>N<sub>4</sub> for the Degradation of Methylene Blue in Water.

Langmuir : the ACS journal of surfaces and colloids·2026
Same author

A High-Performance Solid-State Secondary Battery Using a Triple-Phase-Interface Anode Displaying Excellent Capacity and Electrochemical Kinetics.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Integrating Protein Language Models with Multimodal Embeddings to Accelerate Function Prediction of Uncharacterized Proteins.

International journal of molecular sciences·2026
Same author

Enabling High-Performance Lithium Metal Batteries by Stabilizing the Anode Interface with a Trace 6FDA Additive.

ACS applied materials & interfaces·2026
Same author

Transforming Interfacial Reactivity Into Stability for Durable High-Current Solid-State Sodium Batteries.

Angewandte Chemie (International ed. in English)·2026

相关实验视频

Updated: Jul 20, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

42.6K

一种新的PCB表面缺陷检测方法,基于分离的全球上下文注意力,以指导剩余的上下文聚合.

Lingyun Zhu1, Renyan Zhao2

  • 1College of Computer Science and Engineering, Chongqing University of Technology, Chongqing, 400054, China. zhulingyun@cqut.edu.cn.

Scientific reports
|March 21, 2025
PubMed
概括

通过提高精度和回忆,SRN_Net增强了印刷电路板 (PCB) 制造的小型物体检测. 这种新的框架有效地在复杂的背景下识别小缺陷,提高整体产品质量.

更多相关视频

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
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

448

相关实验视频

Last Updated: Jul 20, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

42.6K
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
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

448

科学领域:

  • 计算机视觉 计算机视觉
  • 机器学习 机器学习
  • 工业自动化 工业自动化

背景情况:

  • 印刷电路板 (PCB) 制造业面临着影响产品性能的缺陷的挑战.
  • 在PCB缺陷识别中的错误检测通常来自小缺陷和复杂的背景.

研究的目的:

  • 推出SRN_Net,一个创新的小型物体检测框架,专门用于PCB缺陷识别.
  • 提高工业环境中检测小缺陷的准确性和稳定性.

主要方法:

  • 开发了SRN_Net,结合了分离的全球上下文注意力 (SGC) 机制,以改善小目标的关注.
  • 集成了一个残余上下文聚合 (RCA) 模块,以减少背景噪声干扰.
  • 采用无脚步卷积 (NSC) 技术,以最大限度地减少卷积过程中的特征损失.

主要成果:

  • 与最先进的方法相比,SRN_Net在PCB数据集上表现出卓越的性能,精度增加了1.1%,回忆率增加了1.3%,mAP@0.5增加了0.6%,mAP@0.5:0.95增加了4.6%.
  • 在NEU表面缺陷数据集上实现了75.8%的mAP,验证了其跨领域的适用性.

结论:

  • SRN_Net有效地解决了PCB缺陷识别中小物体检测的挑战.
  • 拟议的框架为实际的工业应用提供了更好的准确性和稳定性.