PulseAugur
中
实时 08:50:05
English(EN) Urdu Katib Handwritten Dataset: A Historical Document Dataset for Offline Urdu Handwritten Text Recognition with CRNN-Based Baseline Evaluation

新数据集和CRNN模型推动乌尔都语手写文本识别

作者 PulseAugur 编辑部 · [2 个来源] ·

研究人员推出了Urdu Katib Handwritten Dataset (UKHD)，这是第一个历史乌尔都语手写文本行的离线数据集。该数据集旨在解决乌尔都语手写文本识别 (UHTR) 资源稀缺的问题。研究还评估了各种基于CRNN的模型，确定CNN-BGRU-CTC在乌尔都语Katib手写识别方面最有效，实现了较低的字符和单词错误率。 AI

影响 该数据集和模型评估可能会促进历史乌尔都语文字识别的进一步发展，有助于文化遗产的保护。

排序理由 该集群描述了一个新的学术数据集和特定识别任务的模型评估，符合研究类别。

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CL TIER_1 English(EN) · Ramza Basharat, Muhammad Usman Ali ·

    Urdu Katib Handwritten Dataset: A Historical Document Dataset for Offline Urdu Handwritten Text Recognition with CRNN-Based Baseline Evaluation

    arXiv:2606.19139v1 Announce Type: cross Abstract: Automatic Handwritten Text Recognition (HTR) is inherently a challenging task, and its complexity is further increased when dealing with cursive scripts. Although significant efforts have been made on various cursive scripts, rese…

  2. arXiv cs.CV TIER_1 English(EN) · Muhammad Usman Ali ·

    Urdu Katib 手写数据集：用于离线乌尔都语手写文本识别的历史文献数据集，附带基于 CRNN 的基线评估

    Automatic Handwritten Text Recognition (HTR) is inherently a challenging task, and its complexity is further increased when dealing with cursive scripts. Although significant efforts have been made on various cursive scripts, research regarding Urdu Handwritten Text Recognition (…

相关实体

相关话题