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

Advances in Digital Holography, 3-D Imaging, and Optical Information Processing: introduction.

Biomedical optics express·2026
Same author

3D-DeepZern: a deep convolutional neural network for tomographic reconstruction based on Zernike polynomials.

Applied optics·2026
Same author

Deep learning caustic image generation.

Applied optics·2026
Same author

Advances in digital holography, 3-D imaging, and optical information processing: introduction.

Applied optics·2026
Same author

Advances in digital holography, 3-D imaging, and optical information processing: introduction.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same author

Optimizing targeting performance for superband optical systems.

Applied optics·2026

相关实验视频

Updated: Sep 11, 2025

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

43.0K

作为图像分类算法性能预测器的Fλ/d.

Jonathan G Hixson, Brian Teaney, Michael F Finch

    Applied optics
    |August 12, 2025
    PubMed
    概括

    这项研究表明,传感器的FLD指标如何影响YOLO物体检测. 较低的FLD值表明图像质量较差,降低了YOLOv3和YOLOv10算法的检测概率.

    科学领域:

    • 计算机视觉 计算机视觉
    • 机器学习 机器学习
    • 传感器技术 传感器技术

    背景情况:

    • 像YOLO这样的机器学习算法对于对象分类至关重要.
    • 传感器性能指标,如FLD (全宽半最大) 度量,可以显著影响算法结果.
    • 在不同的传感器条件下评估算法性能对于现实世界的应用是必不可少的.

    研究的目的:

    • 调查传感器FLD度量变化的影响对YOLO对象分类性能的影响.
    • 建立FLD指标与YOLOv3和YOLOv10.0检测概率之间的关系.
    • 为基于传感器FLD值评估算法性能提供建议.

    主要方法:

    • 在标准的Teledyne FLIR系统数据集上训练了YOLO_v3和YOLO_v10算法.
    • 一个单独的测试数据集的图像质量降低,以模拟一系列FLD指标值 (0.339到7.98).
    • 在退化数据集上评估YOLO算法性能,以确定在不同FLD级别检测的概率.

    主要成果:

    • 在各种图像退化级别中评估了YOLO_v3和YOLO_v10算法的性能.
    • 观察到FLD指标与两种YOLO版本检测概率之间的相关性.
    • 结果表明,随着FLD值的下降,检测概率降低 (表明图像质量较差).

    更多相关视频

    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
    11:38

    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

    Published on: October 4, 2024

    691
    Fluorescence Recovery after Merging a Droplet to Measure the Two-dimensional Diffusion of a Phospholipid Monolayer
    07:54

    Fluorescence Recovery after Merging a Droplet to Measure the Two-dimensional Diffusion of a Phospholipid Monolayer

    Published on: October 15, 2015

    8.2K

    相关实验视频

    Last Updated: Sep 11, 2025

    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

    43.0K
    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
    11:38

    Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

    Published on: October 4, 2024

    691
    Fluorescence Recovery after Merging a Droplet to Measure the Two-dimensional Diffusion of a Phospholipid Monolayer
    07:54

    Fluorescence Recovery after Merging a Droplet to Measure the Two-dimensional Diffusion of a Phospholipid Monolayer

    Published on: October 15, 2015

    8.2K

    结论:

    • FLD指标是影响YOLO对象分类算法的性能的一个重要因素.
    • 算法性能评估应考虑传感器的FLD指标,以预测现实世界的有效性.
    • 提供了在算法性能评估中使用FLD指标的建议.