Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscripts

• URL: http://arxiv.org/abs/2608.18696v1
• Date: Wed, 19 Aug 2026 08:50:45 GMT
• Title: Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscripts
• Abstract summary: We introduce a local traditional OCR pipeline, which can be iteratively fine-tuned on the target manuscript at the layout-level and the appearance-level.<n>We digitize text from three complex historical manuscripts and introduce a dataset with granular layout-level annotations, along with Unicode annotations in the standard PAGE-XML format.<n>We demonstrate quantitative gains due to iterative fine-tuning of the proposed traditional OCR pipeline, and also benchmark the performance of leading Multi-Modal Large Language Models on the dataset introduced.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Digitizing the text from handwritten historical manuscripts is required to make them easily accessible, preservable, and to enable historical scholars to study them in new ways. Historical manuscripts, however, often exhibit complex heterogeneous layouts and non-standard appearance due to period-specific writing styles, page textures, camera noise, and other nuisance factors, making them difficult to perform OCR on. To tackle this challenge, we introduce a local traditional OCR pipeline, which can be iteratively fine-tuned on the target manuscript at the layout-level and the appearance-level. By adapting to the target manuscript distribution, the proposed Traditional OCR pipeline makes better predictions on subsequent pages, causing iterative reduction in human annotation effort, which is expensive and time-consuming as it requires historical domain expertise. Using this pipeline, we digitize text from three complex historical Sanskrit manuscripts and introduce a dataset with granular layout-level annotations, along with Unicode annotations in the standard PAGE-XML format. We demonstrate quantitative gains due to iterative fine-tuning of the proposed traditional OCR pipeline, and also benchmark the performance of leading Multi-Modal Large Language Models on the introduced Dataset. Code and dataset are available at: https://github.com/flame-cai/gnn-synthetic-layout-historical/.

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• TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents [50.64307290680222]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)
• Persian Pixel: A large-scale synthetic OCR dataset for Persian language [0.0]
  This paper introduces Persian Pixel, a comprehensive synthetic OCR dataset specifically designed to address these challenges.<n>The dataset spans sentence, paragraph, and full-page document layouts generated from a carefully curated seven-million-word Persian corpus.<n>The generation pipeline faithfully models the typographic characteristics of Persian script, including contextual character joining, positional glyph variants, diacritic placement, and multiple representative Persian typefaces.
  arXiv  Detail & Related papers  (2026-07-22T17:13:25Z)
• A Text Recognition Dataset from Sahidic Coptic Ancient Manuscripts [43.31909972506497]
  We introduce SCAM (Sahidic Coptic Ancient Manuscripts), a new line-level dataset built from digitized ancient manuscripts written in the extinct Sahidic Coptic dialect.<n>SCAM poses significant linguistic challenges due to the scarcity of resources for Sahidic Coptic, its uncommon alphabet, and dialect-specific diacritics.<n>We benchmark several state-of-the-art approaches based on different paradigms, highlighting their limitations and strengths in this setting.
  arXiv  Detail & Related papers  (2026-06-14T19:26:42Z)
• FP-THD: Full page transcription of historical documents [0.0]
  This work proposes a pipeline for the transcription of historical documents preserving special features.<n>We analyze historical text images using a layout analysis model to extract text lines, which are then processed by an OCR model to generate a fully digitized page.
  arXiv  Detail & Related papers  (2026-01-20T07:13:38Z)
• ICDAR 2025 Competition on FEw-Shot Text line segmentation of ancient handwritten documents (FEST) [5.794214983347422]
  Few-Shot Text Line of Ancient Handwritten Documents (FEST) Competition.<n>Participants are tasked with developing systems capable of segmenting text lines in U-DIADS-TL dataset, using only three annotated images per manuscript for training.<n> dataset features a diverse collection of ancient manuscripts exhibiting a wide range of layouts, degradation levels, and non-standard formatting, closely reflecting real-world conditions.
  arXiv  Detail & Related papers  (2025-09-16T11:17:03Z)
• Discourse Features Enhance Detection of Document-Level Machine-Generated Content [53.41994768824785]
  Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation.<n>Existing MGC detectors often focus solely on surface-level information, overlooking implicit and structural features.<n>We introduce novel methodologies and datasets to overcome these challenges.
  arXiv  Detail & Related papers  (2024-12-17T08:47:41Z)
• Reference-Based Post-OCR Processing with LLM for Precise Diacritic Text in Historical Document Recognition [1.6941039309214678]
  We propose a method utilizing available content-focused ebooks as a reference base to correct imperfect OCR-generated text.<n>This technique generates high-precision pseudo-page-to-page labels for diacritic languages.<n>The pipeline eliminates various types of noise from aged documents and addresses issues such as missing characters, words, and disordered sequences.
  arXiv  Detail & Related papers  (2024-10-17T08:05:02Z)
• Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domain [53.22419717434372]
  We propose a new task, namely stylized data-to-text generation, whose aim is to generate coherent text according to a specific style. This task is non-trivial, due to three challenges: the logic of the generated text, unstructured style reference, and biased training samples. We propose a novel stylized data-to-text generation model, named StyleD2T, comprising three components: logic planning-enhanced data embedding, mask-based style embedding, and unbiased stylized text generation.
  arXiv  Detail & Related papers  (2023-05-05T03:02:41Z)
• Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions [52.250269529057014]
  Handwritten Text Recognition (HTR) in free-volution pages is a challenging image understanding task. We propose to adopt deformable convolutions, which can deform depending on the input at hand and better adapt to the geometric variations of the text.
  arXiv  Detail & Related papers  (2022-08-17T06:55:54Z)
• Digital Editions as Distant Supervision for Layout Analysis of Printed Books [76.29918490722902]
  We describe methods for exploiting this semantic markup as distant supervision for training and evaluating layout analysis models. In experiments with several model architectures on the half-million pages of the Deutsches Textarchiv (DTA), we find a high correlation of these region-level evaluation methods with pixel-level and word-level metrics. We discuss the possibilities for improving accuracy with self-training and the ability of models trained on the DTA to generalize to other historical printed books.
  arXiv  Detail & Related papers  (2021-12-23T16:51:53Z)
• Rethinking Text Line Recognition Models [57.47147190119394]
  We consider two decoder families (Connectionist Temporal Classification and Transformer) and three encoder modules (Bidirectional LSTMs, Self-Attention, and GRCLs) We compare their accuracy and performance on widely used public datasets of scene and handwritten text. Unlike the more common Transformer-based models, this architecture can handle inputs of arbitrary length.
  arXiv  Detail & Related papers  (2021-04-15T21:43:13Z)
• Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation [50.01708049531156]
  We focus on a new practical task, document-scale text content manipulation, which is the opposite of text style transfer. In detail, the input is a set of structured records and a reference text for describing another recordset. The output is a summary that accurately describes the partial content in the source recordset with the same writing style of the reference.
  arXiv  Detail & Related papers  (2020-02-24T12:52:10Z)

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.