Scholarlink

<p>The Ethiopic script used in the Amharic Language presents persistent challenges for Optical Character Recognition (OCR) due to its large character vocabulary, diacritics, and high variability in handwriting. Although Amharic is spoken by over 58 million people, progress in OCR has been constrained by the lack of large, diverse, sentence-level datasets. Existing datasets are small, synthetic-only, or limited to character- or word-level annotations, preventing models from capturing the complexity of real documents. We introduce <b>Fidel</b>, the first large-scale Amharic OCR dataset spanning handwritten, typed, and synthetic text. Fidel contains 40k handwritten and 28k typed line images collected from 411 native writers, providing broad coverage of handwriting styles and modern vocabulary. We further formalise our approach as a scalable data acquisition and preprocessing pipeline, deskewing, line extraction, and alignment, designed to guide future dataset creation for low-resource scripts. To complement the real data, we generate high-quality synthetic Amharic text images to support robust model training. Using Fidel, we construct the first comprehensive benchmark for Amharic OCR, evaluating <b>seven deep learning based OCR models</b>. These models span CNN, CTC, transformer and hybrid architectures, enabling a robust assessment of domain transfer and modality-specific performance across handwritten, typed, and synthetic text. The best-performing model trained on Fidel achieves state-of-the-art results, with a CER of 2.64% and WER of 7.29%, demonstrating the substantial impact of our dataset on advancing practical, high-accuracy Amharic OCR.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Fidel: a large-scale sentence level Amharic OCR dataset

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月7日

查看全文
  • Tunga Tessema Chamisso,
  • Blessed Guda,
  • Bereket Retta,
  • Carmel Prosper Sagbo,
  • Gabrial Zencha Ashungafac,
  • Assane Gueye

摘要

The Ethiopic script used in the Amharic Language presents persistent challenges for Optical Character Recognition (OCR) due to its large character vocabulary, diacritics, and high variability in handwriting. Although Amharic is spoken by over 58 million people, progress in OCR has been constrained by the lack of large, diverse, sentence-level datasets. Existing datasets are small, synthetic-only, or limited to character- or word-level annotations, preventing models from capturing the complexity of real documents. We introduce Fidel, the first large-scale Amharic OCR dataset spanning handwritten, typed, and synthetic text. Fidel contains 40k handwritten and 28k typed line images collected from 411 native writers, providing broad coverage of handwriting styles and modern vocabulary. We further formalise our approach as a scalable data acquisition and preprocessing pipeline, deskewing, line extraction, and alignment, designed to guide future dataset creation for low-resource scripts. To complement the real data, we generate high-quality synthetic Amharic text images to support robust model training. Using Fidel, we construct the first comprehensive benchmark for Amharic OCR, evaluating seven deep learning based OCR models. These models span CNN, CTC, transformer and hybrid architectures, enabling a robust assessment of domain transfer and modality-specific performance across handwritten, typed, and synthetic text. The best-performing model trained on Fidel achieves state-of-the-art results, with a CER of 2.64% and WER of 7.29%, demonstrating the substantial impact of our dataset on advancing practical, high-accuracy Amharic OCR.