Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition

  • 类型:arxiv
  • 标识:1406.2227
  • 链接:https://arxiv.org/abs/1406.2227
  • 主题:evaluation
  • 主分类:multimodal
  • 形态:method
  • 被引:1000
  • 被引来源:Semantic Scholar
  • S2被引:1000
  • OpenAlex被引:809
  • 影响力被引:119
  • TLDR:This work presents a framework for the recognition of natural scene text that does not require any human-labelled data, and performs word recognition on the whole image holistically, departing from the character based recognition systems of the past.
  • OpenAlex ID:W1491389626
  • OpenAlex DOI:10.48550/arxiv.1406.2227
  • DOI:10.48550/arxiv.1406.2227
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://arxiv.org/pdf/1406.2227
  • OpenAlex更新:2026-08-01
  • 待LLM分类:否
  • 成熟度:research
  • 场景:scene text recognition、synthetic data、OCR
  • 标题中文:Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
  • TLDR中文:本文提出了一个自然场景文本识别框架,无需任何人工标注数据,并以整体方式对整幅图像进行单词识别,区别于过去基于字符的识别系统。
  • 来源文件
  • [OpenAlex discover]
  • [S2 enrich]