How Far Can Synthetic Data Take Thai OCR?

• URL: http://arxiv.org/abs/2609.03595v1
• Date: Thu, 03 Sep 2026 09:46:19 GMT
• Title: How Far Can Synthetic Data Take Thai OCR?
• Abstract summary: We build a Thai OCR model adapted without OCR labels from real Thai document pages.<n>Synthetic data provide exact labels at scale, but "realism" conflates source domain, page context, typography, spatial structure, and glyph variation.<n>We evaluate each variant under page- and crop-level training on printed and handwritten Thai documents.
• Score: 3.8641218447429657
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We investigate what makes synthetic OCR supervision transfer to real Thai documents and use the resulting insights to build Wayu-Paxa-OCR-Zero, a Thai OCR model adapted without OCR labels from real Thai document pages. Synthetic data provide exact labels at scale, but "realism" conflates source domain, page context, typography, spatial structure, and glyph variation. We disentangle these factors with a controlled document-reconstruction pipeline and evaluate each variant under page- and crop-level training on printed and handwritten Thai documents. Non-text context has little consistent effect, whereas typeface diversity, two-dimensional structure, and real handwriting glyphs improve transfer; moreover, source-domain matching depends on training granularity, with in-domain reconstruction approaching real printed supervision under page-level training (1.82% versus 1.31% median character error rate) but underperforming out-of-domain reconstruction under crop-level training (15.59% versus 5.52%). Guided by these findings, we adapt the 0.9B-parameter PaddleOCR-VL-1.6 into Wayu-Paxa-OCR-Zero using 45,723 synthetic pages: relative to its base checkpoint, it reduces median character error rate from 6.64% to 1.24% on printed pages and from 74.87% to 20.55% on handwriting and outperforms Typhoon OCR v1 7B on all five evaluation sets, showing that synthetic-only training can be competitive.

Related papers

• TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents [50.64307290680222]
  TongGuOCR is a layout-aware and token-augmented multimodal large language model (MLLM) for OCR of Chinese historical documents.<n>TongGuOCR achieves 93.76 AR and reduces NED from 10.43 to 6.15 and RO-ED from 7.53 to 3.49 relative to the best competing score for each metric.
  arXiv  Detail & Related papers  (2026-08-08T04:50:00Z)
• LV-ROVER-MLT: Low-Resource Maltese OCR by Multi-Stream Voting [0.0]
  This paper reports results on a benchmark against a fine-tuned Tesseract baseline with a character error rate of 0.0234.<n> Ensemble recognition alone, scored under the same label convention as the baseline, improves character error rate by 44 percent to 0.01317.<n>A post-processing chain that aligns Tesseract's straight-quote and dash output to the benchmark's curly-quote convention, plus one stage that recovers misread diacritics, brings the full pipeline to a character error rate of 0.00700.
  arXiv  Detail & Related papers  (2026-06-30T22:58:41Z)
• Cross-Temporal Sinhala OCR: Page-Level Adaptation and Diachronic Analysis [0.0]
  There are no publicly available real-world datasets for page-level Sinhala OCR.<n>We introduce sinhala-ocr-lk-acts-1010, an annotated dataset of 1,010 page-level images and their transcriptions.<n>Three models based on deep learning-based visual language processing are fine-tuned using QLoRA.
  arXiv  Detail & Related papers  (2026-06-28T13:01:54Z)
• DocAtlas: Multilingual Document Understanding Across 80+ Languages [58.715440331861295]
  We introduce DocAtlas, a framework that constructs high-fidelity OCR datasets and benchmarks covering 82 languages.<n>Our dual pipelines, differential rendering of native DOCX documents and synthetic-based generation for right-to-left scripts produce precise structural annotations.
  arXiv  Detail & Related papers  (2026-05-12T18:09:38Z)
• GutenOCR: A Grounded Vision-Language Front-End for Documents [0.42776193697639947]
  We introduce a family of grounded OCR front-ends obtained by fine-tuning Qwen2.5-VL-3B and Qwen2.5-VL-7B.<n>The resulting single-checkpoint vision-language models expose reading, detection, and grounding through a unified, prompt-based interface.<n>We show that GutenOCR-7B more than doubles the composite grounded OCR score of its Qwen2.5-VL-7B backbone on 10.5K held-out business and scientific pages.
  arXiv  Detail & Related papers  (2026-01-20T21:26:15Z)
• Finetuning Vision-Language Models as OCR Systems for Low-Resource Languages: A Case Study of Manchu [0.0]
  Manchu, a critically endangered language, lacks effective OCR systems that can handle real-world historical documents.<n>This study develops high-performing OCR systems by fine-tuning three open-source vision-language models.<n>LLaMA-3.2-11B achieved exceptional performance with 98.3% word accuracy and 0.0024 character error rate on synthetic data.
  arXiv  Detail & Related papers  (2025-07-09T11:38:20Z)
• MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm [60.14048367611333]
  MonkeyOCR is a vision-language model for document parsing.<n>It advances the state of the art by leveraging a Structure-Recognition-Relation (SRR) triplet paradigm.
  arXiv  Detail & Related papers  (2025-06-05T16:34:57Z)
• CLOCR-C: Context Leveraging OCR Correction with Pre-trained Language Models [0.0]
  This paper introduces Context Leveraging OCR Correction (CLOCR-C)<n>It uses the infilling and context-adaptive abilities of transformer-based language models (LMs) to improve OCR quality.<n>The study aims to determine if LMs can perform post-OCR correction, improve downstream NLP tasks, and the value of providing the socio-cultural context as part of the correction process.
  arXiv  Detail & Related papers  (2024-08-30T17:26:05Z)
• LOCR: Location-Guided Transformer for Optical Character Recognition [55.195165959662795]
  We propose LOCR, a model that integrates location guiding into the transformer architecture during autoregression. We train the model on a dataset comprising over 77M text-location pairs from 125K academic document pages, including bounding boxes for words, tables and mathematical symbols. It outperforms all existing methods in our test set constructed from arXiv, as measured by edit distance, BLEU, METEOR and F-measure.
  arXiv  Detail & Related papers  (2024-03-04T15:34:12Z)
• Toward Real Text Manipulation Detection: New Dataset and New Solution [58.557504531896704]
  High costs associated with professional text manipulation limit the availability of real-world datasets. We present the Real Text Manipulation dataset, encompassing 14,250 text images. Our contributions aim to propel advancements in real-world text tampering detection.
  arXiv  Detail & Related papers  (2023-12-12T02:10:16Z)
• PART: Pre-trained Authorship Representation Transformer [52.623051272843426]
  Authors writing documents imprint identifying information within their texts.<n>Previous works use hand-crafted features or classification tasks to train their authorship models.<n>We propose a contrastively trained model fit to learn textbfauthorship embeddings instead of semantics.
  arXiv  Detail & Related papers  (2022-09-30T11:08:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.