UniLipi: A Unified Multi-Script OCR for Historical Indic Manuscripts

• URL: http://arxiv.org/abs/2608.28195v1
• Date: Fri, 28 Aug 2026 11:08:59 GMT
• Title: UniLipi: A Unified Multi-Script OCR for Historical Indic Manuscripts
• Abstract summary: We present UniLipi, a unified multi-script OCR model for handwritten Indic manuscripts trained jointly across 13 Indic scripts within a single framework.<n>UniLipi directly handles realistic manuscript conditions, including extreme variation in line geometry, large variation in line length, and partial interruptions caused by non-textual manuscript entities such as holes, stains, or pictorial illustrations.
• Score: 7.710824610855653
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Optical character recognition (OCR) for handwritten Indic manuscripts is essential for large-scale digitization and computational access to manuscript heritage. However, existing approaches are typically developed for one script at a time and require substantial script-specific customization. This limits scalability and practical deployment across diverse collections. We present UniLipi, a unified multi-script OCR model for handwritten Indic manuscripts trained jointly across 13 Indic scripts within a single framework. UniLipi directly handles realistic manuscript conditions, including extreme variation in line geometry, large variation in line length, and partial interruptions caused by non-textual manuscript entities such as holes, stains, or pictorial illustrations. To operate effectively under ultra low-resource conditions, the model leverages script-aware synthetic manuscript data generation, substantially reducing reliance on large volumes of real annotated data. Beyond historical manuscripts, we show that UniLipi serves as an effective foundational pretrained model. Specifically, its learned representations enable good OCR performance for contemporary Indic handwriting and extend to several non-Indic scripts, including Tibetan, Italian, Latin, and Chinese scripts. In addition to transcription, UniLipi predicts script identity and per-line native character counts, supporting practical manuscript cataloging workflows.

Related papers

• HandwritingAgent: Language-Driven Handwriting Synthesis in Scalable Vector Space [12.612154268994184]
  HandwritingAgent is a language-driven agent that can synthesize natural handwriting sequences directly in SVG format with no need for style-specific training.<n>Experiments on diverse handwriting tasks spanning imitation, recognition, multi-lingual handwriting synthesis, and generation of complex handwritten maths and science expressions indicate substantial improvement in performance.
  arXiv  Detail & Related papers  (2026-06-17T08:02:19Z)
• GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts [58.92151016423978]
  We introduce GlotOCR Bench, a comprehensive benchmark evaluating OCR across 100+ Unicode scripts.<n>Our benchmark comprises clean and degraded image variants rendered from real multilingual texts.<n>We evaluate a broad suite of open-weight and proprietary vision-language models and find that most perform well on fewer than ten scripts.
  arXiv  Detail & Related papers  (2026-04-14T17:12:41Z)
• Zero-Shot Synthetic-to-Real Handwritten Text Recognition via Task Analogies [60.84720484975815]
  Handwritten Text Recognition (HTR) models often struggle to generalize to real text.<n>We tackle the fully zero-shot synthetic-to-real generalization setting.<n>Our approach learns how model parameters change when moving from synthetic to real handwriting in one or more source languages.
  arXiv  Detail & Related papers  (2026-04-08T07:33:31Z)
• DohaScript: A Large-Scale Multi-Writer Dataset for Continuous Handwritten Hindi Text [1.299941371793082]
  We introduce DohaScript, a large scale, multi writer dataset of handwritten Hindi text collected from 531 unique contributors.<n>The dataset is designed as a parallel stylistic corpus, in which all writers transcribe the same fixed set of six traditional Hindi dohas (couplets)<n>DohaScript is intended to serve as a standardized and reproducible benchmark for advancing research on continuous handwritten Devanagari text in low resource script settings.
  arXiv  Detail & Related papers  (2026-02-20T09:25:14Z)
• Linear Script Representations in Speech Foundation Models Enable Zero-Shot Transliteration [70.84108518476744]
  We show that script is linearly encoded in the activation space of multilingual speech models, and that modifying activations at inference time enables direct control over output script.<n>We apply this approach to inducing post-hoc control over the script of speech recognition output, where we observe competitive performance across all model sizes of Whisper.
  arXiv  Detail & Related papers  (2026-01-06T10:45:04Z)
• Handwriting Recognition in Historical Documents with Multimodal LLM [0.0]
  Multimodal Language Models have demonstrated effectiveness in performing OCR and computer vision tasks with few shot prompting. I evaluate the accuracy of handwritten document transcriptions generated by Gemini against the current state of the art Transformer based methods.
  arXiv  Detail & Related papers  (2024-10-31T15:32:14Z)
• Exploring the Role of Transliteration in In-Context Learning for Low-resource Languages Written in Non-Latin Scripts [50.40191599304911]
  We investigate whether transliteration is also effective in improving LLMs' performance for low-resource languages written in non-Latin scripts. We propose three prompt templates, where the target-language text is represented in (1) its original script, (2) Latin script, or (3) both. Our findings show that the effectiveness of transliteration varies by task type and model size.
  arXiv  Detail & Related papers  (2024-07-02T14:51:20Z)
• MetaScript: Few-Shot Handwritten Chinese Content Generation via Generative Adversarial Networks [15.037121719502606]
  We propose MetaScript, a novel content generation system designed to address the diminishing presence of personal handwriting styles in the digital representation of Chinese characters. Our approach harnesses the power of few-shot learning to generate Chinese characters that retain the individual's unique handwriting style and maintain the efficiency of digital typing.
  arXiv  Detail & Related papers  (2023-12-25T17:31:19Z)
• Beyond Arabic: Software for Perso-Arabic Script Manipulation [67.31374614549237]
  We provide a set of finite-state transducer (FST) components and corresponding utilities for manipulating the writing systems of languages that use the Perso-Arabic script. The library also provides simple FST-based romanization and transliteration.
  arXiv  Detail & Related papers  (2023-01-26T20:37:03Z)
• Letter-level Online Writer Identification [86.13203975836556]
  We focus on a novel problem, letter-level online writer-id, which requires only a few trajectories of written letters as identification cues. A main challenge is that a person often writes a letter in different styles from time to time. We refer to this problem as the variance of online writing styles (Var-O-Styles)
  arXiv  Detail & Related papers  (2021-12-06T07:21:53Z)

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.