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

Sequence-specific targeting of VEGFA genomic DNA to inhibit tumor growth.

NPJ precision oncology·2026
Same author

Guiding the Molnupiravir Tablet Formulation Using Physiologically Based Biopharmaceutics Modeling and Successfully Establishing Dissolution Safe Space.

The AAPS journal·2026
Same author

Retraction Note: Deficiency of endothelial sirtuin1 in mice stimulates skeletal muscle insulin sensitivity by modifying the secretome.

Nature communications·2026
Same author

Advances in peptide nucleic acid for targeting RNA and genomic DNA.

Cell reports. Physical science·2026
Same author

Engineered miR-122 inhibitors preserve endothelial mitochondrial function and prevent vascular dysfunction in obesity-associated prediabetes.

Molecular therapy. Nucleic acids·2026
Same author

Asymmetric Synthesis of MK-7845, an Investigational Treatment for COVID-19.

Organic letters·2025

相关实验视频

Updated: Jun 1, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K

基于深度学习的薄膜涂层平板电脑的缺陷检测使用卷积神经网络.

Kabir A Pathak1, Prapti Kafle1, Ajit Vikram2

  • 1Pharmaceutical Sciences and Clinical Supply, Merck & Co., Inc., Rahway, NJ, USA.

International journal of pharmaceutics
|January 20, 2025
PubMed
概括

这项研究引入了一种机器学习方法,用于自动检测薄膜涂层平板电脑缺陷. 开发的卷积神经网络 (CNN) 达到99.7%的准确性,大大提高了药品质量控制的传统方法.

关键词:
卷积神经网络是一种卷积神经网络.缺陷 缺陷 缺陷 缺陷薄膜涂层药片 薄膜涂层药片图像分析 图像分析机器学习是机器学习.

更多相关视频

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K
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

相关实验视频

Last Updated: Jun 1, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.0K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K
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

科学领域:

  • 制药制造业 制药制造业 制药制造业
  • 计算机视觉 计算机视觉
  • 机器学习 机器学习

背景情况:

  • 传统的片视觉检查缺陷是主观和低效的.
  • 自动缺陷检测对于确保药品质量和制造效率至关重要.

研究的目的:

  • 开发和评估一种基于机器学习的新型方法,用于客观有效地检测薄膜涂层平板电脑的缺陷.
  • 将卷积神经网络 (CNN) 的性能与基于静态规则的方法进行比较.

主要方法:

  • 膜片片中的手动诱导的缺陷 (破碎,破碎,颜色不均,斑点).
  • 使用3D打印托盘和独特的细分方法进行图像采集.
  • 在25,200张增强图像上训练CNN以进行多类缺陷分类.

主要成果:

  • 美国有线电视新闻网 (CNN) 模型在检测薄膜涂层平板电脑中的缺陷方面达到99.7%的准确性.
  • 美国有线电视新闻网显著优于基于静态规则的方法,该方法在维度分析中显示出高错误率.
  • 该模型通过数据增强技术证明了它的稳定性.

结论:

  • 拟议的基于CNN的图像分析提供了一种标准化,客观和高效的方法来检测药品平板电脑缺陷.
  • 这种方法为提高产品质量和加速制药开发提供了有价值的工具.