Digitizing Nepal's Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts

• URL: http://arxiv.org/abs/2512.17111v1
• Date: Thu, 18 Dec 2025 22:43:15 GMT
• Title: Digitizing Nepal's Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts
• Abstract summary: This paper presents the first end-to-end pipeline for Handwritten Text Recognition for Old Nepali.<n>We adopt a line-level transcription approach and systematically explore encoder-decoder architectures and data-centric techniques to improve recognition accuracy.
• Score: 0.3899824115379246
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents the first end-to-end pipeline for Handwritten Text Recognition (HTR) for Old Nepali, a historically significant but low-resource language. We adopt a line-level transcription approach and systematically explore encoder-decoder architectures and data-centric techniques to improve recognition accuracy. Our best model achieves a Character Error Rate (CER) of 4.9\%. In addition, we implement and evaluate decoding strategies and analyze token-level confusions to better understand model behaviour and error patterns. While the dataset we used for evaluation is confidential, we release our training code, model configurations, and evaluation scripts to support further research in HTR for low-resource historical scripts.

Related papers

• Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscripts [0.0]
  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.
  arXiv  Detail & Related papers  (2026-08-19T08:50:45Z)
• 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)
• Online Writer Retrieval with Chinese Handwritten Phrases: A Synergistic Temporal-Frequency Representation Learning Approach [53.189911918976655]
  We propose DOLPHIN, a novel retrieval model designed to enhance handwriting representations through synergistic temporal-frequency analysis.<n>We introduce OLIWER, a large-scale online writer retrieval dataset encompassing over 670,000 Chinese handwritten phrases from 1,731 individuals.<n>Our findings emphasize the significance of point sampling frequency and pressure features in improving handwriting representation quality.
  arXiv  Detail & Related papers  (2024-12-16T11:19:22Z)
• General Detection-based Text Line Recognition [15.761142324480165]
  We introduce a general detection-based approach to text line recognition, be it printed (OCR) or handwritten (HTR)<n>Our approach builds on a completely different paradigm than state-of-the-art HTR methods, which rely on autoregressive decoding.<n>We improve state-of-the-art performances for Chinese script recognition on the CASIA v2 dataset, and for cipher recognition on the Borg and Copiale datasets.
  arXiv  Detail & Related papers  (2024-09-25T17:05:55Z)
• FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback [69.4639239117551]
  FigCaps-HF is a new framework for figure-caption generation that incorporates domain expert feedback in generating captions optimized for reader preferences.<n>Our framework comprises of 1) an automatic method for evaluating quality of figure-caption pairs, 2) a novel reinforcement learning with human feedback (RLHF) method to optimize a generative figure-to-caption model for reader preferences.
  arXiv  Detail & Related papers  (2023-07-20T13:40:22Z)
• Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency [71.42261918225773]
  Conceptually, LOCCO can be viewed as a form of self-learning where the semantic being trained is used to generate annotations for unlabeled text. As an added bonus, the annotations produced by LOCCO can be trivially repurposed to train a neural text generation model.
  arXiv  Detail & Related papers  (2023-05-31T16:47:20Z)
• How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning [23.274139396706264]
  Recent advancements in Deep Learning-based Handwritten Text Recognition (HTR) have led to models with remarkable performance on modern and historical manuscripts. Those models struggle to obtain the same performance when applied to manuscripts with peculiar characteristics, such as language, paper support, ink, and author handwriting. In this paper, we take into account large, real benchmark datasets and synthetic ones obtained with a styled Handwritten Text Generation model. We give a quantitative indication of the most relevant characteristics of such data for obtaining an HTR model able to effectively transcribe manuscripts in small collections with as little as five real fine-tuning lines
  arXiv  Detail & Related papers  (2023-05-04T07:00:28Z)
• Uncovering the Handwritten Text in the Margins: End-to-end Handwritten Text Detection and Recognition [0.840835093659811]
  This work presents an end-to-end framework for automatic detection and recognition of handwritten marginalia. It uses data augmentation and transfer learning to overcome training data scarcity. The effectiveness of the proposed framework has been empirically evaluated on the data from early book collections found in the Uppsala University Library in Sweden.
  arXiv  Detail & Related papers  (2023-03-10T14:00:53Z)
• Quality-Aware Decoding for Neural Machine Translation [64.24934199944875]
  We propose quality-aware decoding for neural machine translation (NMT) We leverage recent breakthroughs in reference-free and reference-based MT evaluation through various inference methods. We find that quality-aware decoding consistently outperforms MAP-based decoding according both to state-of-the-art automatic metrics and to human assessments.
  arXiv  Detail & Related papers  (2022-05-02T15:26:28Z)
• AttentionHTR: Handwritten Text Recognition Based on Attention Encoder-Decoder Networks [0.0]
  This work proposes an attention-based sequence-to-sequence model for handwritten word recognition. It exploits models pre-trained on scene text images as a starting point towards tailoring the handwriting recognition models. The effectiveness of the proposed end-to-end HTR system has been empirically evaluated on a novel multi-writer dataset.
  arXiv  Detail & Related papers  (2022-01-23T22:48:36Z)
• Lexically Aware Semi-Supervised Learning for OCR Post-Correction [90.54336622024299]
  Much of the existing linguistic data in many languages of the world is locked away in non-digitized books and documents. Previous work has demonstrated the utility of neural post-correction methods on recognition of less-well-resourced languages. We present a semi-supervised learning method that makes it possible to utilize raw images to improve performance.
  arXiv  Detail & Related papers  (2021-11-04T04:39:02Z)
• One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition [10.473427493876422]
  Low resource Handwritten Text Recognition is a hard problem due to the scarce annotated data and the very limited linguistic information. In this paper we address this problem through a data generation technique based on Bayesian Program Learning. Contrary to traditional generation approaches, which require a huge amount of annotated images, our method is able to generate human-like handwriting using only one sample of each symbol from the desired alphabet.
  arXiv  Detail & Related papers  (2021-05-11T18:53:01Z)
• Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation [81.55533657694016]
  We propose a Hierarchical bi-directional self-attention Network framework (HabNet) for paper review rating prediction and recommendation. Specifically, we leverage the hierarchical structure of the paper reviews with three levels of encoders: sentence encoder (level one), intra-review encoder (level two) and inter-review encoder (level three) We are able to identify useful predictors to make the final acceptance decision, as well as to help discover the inconsistency between numerical review ratings and text sentiment conveyed by reviewers.
  arXiv  Detail & Related papers  (2020-11-02T08:07:50Z)

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.