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

相关实验视频

Updated: Jul 2, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

reCAPTCHA:通过网络安全措施实现基于人类的字符识别.

Luis von Ahn1, Benjamin Maurer, Colin McMillen

  • 1Computer Science Department, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA 15213, USA. biglou@cs.cmu.edu

Science (New York, N.Y.)
|August 16, 2008
PubMed
概括
此摘要是机器生成的。

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

Maus's salts: an old family of iron sulfates with possible magnetic frustration.

Acta crystallographica Section B, Structural science, crystal engineering and materials·2026
Same author

Systemic sclerosis-associated pulmonary arterial hypertension and pulmonary fibrosis: exploring biomarker discriminators with advanced omics in a Caucasian cohort.

Frontiers in immunology·2026
Same author

The dopamine D3 receptor regulates dopamine-induced activation and glycolytic metabolism of synovial fibroblasts in rheumatoid arthritis.

Clinical and experimental immunology·2026
Same author

Engaging the PD-1 pathway in systemic sclerosis attenuates inflammation-driven fibrosis.

Annals of the rheumatic diseases·2026
Same author

Development of Dirofilaria immitis adult worms in NSG mice, detection of parasite-derived microRNA and comparative analysis of laboratory isolates.

Scientific reports·2026
Same author

Lymphocyte Activation Gene 3 Regulation of Profibrotic Cytokines and Type I Collagen Production in Patients With Systemic Sclerosis.

ACR open rheumatology·2026

完全自动化的公共图灵测试来区分计算机和人类 (CAPTCHA) 现在可以数字化旧书籍. 这种方法准确地转写未识别的文本,与专业的人类标准相匹配,并处理数百万个单词.

科学领域:

  • 人与计算机的交互
  • 数字人文学科 数字人文学科
  • 信息安全 信息安全

背景情况:

  • 通过要求人类执行任务,CAPTCHA是防止在线服务自动滥用的安全措施.
  • 传统的CAPTCHA涉及破译扭曲的字符,这是一项计算机难以完成的任务.

研究的目的:

  • 调查人类解决CAPTCHA的努力是否可以重新用于有用的任务.
  • 从历史文档中扫描的难以OCR (光学字符识别) 的文本进行数字化.

主要方法:

  • 用户可以从旧书中扫描出OCR软件无法识别的单词.
  • 该系统收集了这些单词的人类生成的转录,以构建一个数据集.

主要成果:

  • 该方法在转录文本时实现了超过99%的单词准确性.
  • 这种准确度水平与专业的人体转录器的准确度相当.
  • 该系统已在超过4万个网站上实施,已转录了超过4.4亿个单词.

结论:

  • 由人类驱动的CAPTCHA系统可以有效地将传统印刷材料数字化.
  • 这种方法为文本数字化挑战提供了可扩展和准确的解决方案.

更多相关视频

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)

Published on: April 8, 2019

相关实验视频

Last Updated: Jul 2, 2026

Artificial Intelligence-Based System for Detecting Attention Levels in Students
06:37

Artificial Intelligence-Based System for Detecting Attention Levels in Students

Published on: December 15, 2023

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)
05:57

Long-term Video Tracking of Cohoused Aquatic Animals: A Case Study of the Daily Locomotor Activity of the Norway Lobster (Nephrops norvegicus)

Published on: April 8, 2019

  • 安全和数据创建的双重目的为CAPTCHA技术提供了一个新的应用.