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

An attention-infused deep convolutional paradigm for multi-label classification of thoracic pathologies in chest radiographs.

Scientific reports·2026
Same author

Boron supplementation enhances yield, photosynthetic efficiency, enzyme activity, and mineral content in Persian clover (Trifolium resupinatum L.).

Die Naturwissenschaften·2026
Same author

Negative pressure intrusion cementation versus tourniquet use in total knee arthroplasty: optimising cement mantle thickness.

European journal of orthopaedic surgery & traumatology : orthopedie traumatologie·2026
Same author

Decoding the Role of Nutrition and Foods in Augmenting Athletes Performance: A Review.

Current drug research reviews·2026
Same author

Correction: Sensitivity-informed framework for enrichment distribution in MNR for thermal performance enhancement.

Scientific reports·2026
Same author

Clinical Predictors of In-Hospital Mortality among Patients with Stent Thrombosis Following Primary Percutaneous Coronary Intervention Using Drug-Eluting Stents.

Journal of the College of Physicians and Surgeons--Pakistan : JCPSP·2026

相关实验视频

Updated: Jun 16, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K

在摄像头中检测到巴什图文字和图形,使用深度学习模型捕获了巴什图文档图像.

Khan Bahadar1, Riaz Ahmad1, Khursheed Aurangzeb2

  • 1Department of Computer Science, Shaheed Benazir Bhutto University, Sheringal, Pakistan.

PeerJ. Computer science
|August 15, 2024
PubMed
概括

这项研究引入了一种新的深度学习方法,用于分析巴什图文档图像,准确检测文本和图形. 它提供了一个新的数据集,并实现了84.90%的mAP,为代表性不足的语言推进了文档图像分析.

关键词:
深度学习是一种深度学习.文件图像 文档图像 文档图像图形检测检测可以通过图形检测检测.脚本检测 脚本检测

更多相关视频

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

496
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K

相关实验视频

Last Updated: Jun 16, 2025

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis
05:41

A Step-by-Step Implementation of DeepBehavior, Deep Learning Toolbox for Automated Behavior Analysis

Published on: February 6, 2020

9.4K
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

496
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.7K

科学领域:

  • 计算机科学 计算机科学
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 布局分析对于文档图像分析 (DIA) 来说至关重要,但对于巴什图文档来说未被充分探索.
  • 现有的DIA系统缺乏针对普什图文本和图形的特定模型.
  • 普什图文档的独特视觉特征带来了一个重大挑战.

研究的目的:

  • 开发基于深度学习的分类器,用于检测文档图像中的巴什图文本和图形.
  • 为研究和开发创建一个新的,现实世界的普什托文档数据集.
  • 为了建立巴什图文档布局分析的基准.

主要方法:

  • 开发一种深度学习分类器,使用一种更快的R-CNN变体,特别是单射击探测器 (SSD).
  • 创建一个新的数据集,包括超过1000个摄像机捕获的普什图文档图像.
  • 卷积神经网络 (CNN) 的应用用于特征提取和分类.

主要成果:

  • 在300张巴什图文档图像的测试组上,获得了84.90%的平均平均精度 (mAP).
  • 成功证明了能够区分巴什图文本和图形元素的能力.
  • 验证了拟议的基于SSD的深度学习模型的有效性,用于巴什图文档布局分析.

结论:

  • 拟议的深度学习模型有效地对普什图文档进行布局分析,这是以前未经探索的领域.
  • 新创建的普什图文档数据集是DIA未来研究的宝贵资源.
  • 这项工作为低资源语言的文档图像分析领域做出了重大贡献.