arXiv cs.CL· Faizan Iqbal, Haq Nawaz Malik, Hafsah Pervaiz·· 11 小时前AI 评分31
从零构建 OCR：面向低资源文种的数据中心化框架
From Zero to OCR: A Data-Centric Framework for Unsupported Low-Resource Scripts
AI 导读
研究者提出一套数据中心化框架，仅用无标注文本语料和数字字体即可为缺乏标注的低资源文种构建端到端 OCR，无需人工标注任何训练图像。该框架在约 680 万使用者的克什米尔语 Nastaliq 文种上验证，词级识别 CER 为 0.39%，合成页面 10.0%，浏览器渲染数字页面 13.5%，并给出排版书籍页面 18.45%、退化历史文档 49.8% 的参考结果。
正文 · 原文
Abstract:Optical character recognition (OCR) remains inaccessible to many low-resource scripts because annotated document images are unavailable and synthetic training data can fail to preserve script-specific visual structure. We present a data-centric framework that builds end-to-end OCR for such scripts from only an unannotated text corpus and digital fonts, without manually annotating a single training image. A synthetic data engine renders word, line and page images with correct complex-script shaping and automatically derived labels; a YOLOv8 word detector and a convolutional recurrent recognizer trained with connectionist temporal classification learn from these images; and a stage-gate evaluation protocol isolates recognition error before detection is introduced. We demonstrate the framework on Kashmiri, a Perso-Arabic Nastaliq script with approximately 6.8 million speakers that none of six widely used OCR engines supports. Three line-level recognizers, including one transferred from Arabic, stalled between 41% and 79% character error rate (CER), motivating a word-level formulation; subsequent improvements came primarily from rendering fidelity, diacritic-preserving crop margins and tuned non-maximum suppression. The resulting system achieves 0.39% CER on held-out words, 10.0% on synthetic pages and 13.5% on browser-rendered digital pages, and establishes reference results of 18.45% on typeset book pages and 49.8% on degraded historical documents. We publicly release the trained models, the inference code and a synthetic dataset of 285,864 Kashmiri text-line images, and we describe a step-by-step procedure for building OCR for other unsupported scripts.
| Comments: | 9 pages, 9 figures, 4 tables. Model: this https URL |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.00078 [cs.CV] |
| (or arXiv:2611.00078v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.00078 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Faizan Iqbal [view email]
[v1]
Sun, 18 Oct 2026 08:18:16 UTC (1,925 KB)
来源：arXiv cs.CL · arxiv.org