Training Kindai OCR with parallel textline images and self-attention feature distance-based loss

• URL: http://arxiv.org/abs/2508.08537v1
• Date: Tue, 12 Aug 2025 01:01:32 GMT
• Title: Training Kindai OCR with parallel textline images and self-attention feature distance-based loss
• Abstract summary: We introduce a distance-based objective function that minimizes the gap between self-attention features of parallel image pairs.<n>Our approach improves the discriminative quality of self-attention representations, leading to more effective OCR performance for historical documents.
• Score: 0.6767885381740952
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Kindai documents, written in modern Japanese from the late 19th to early 20th century, hold significant historical value for researchers studying societal structures, daily life, and environmental conditions of that period. However, transcribing these documents remains a labor-intensive and time-consuming task, resulting in limited annotated data for training optical character recognition (OCR) systems. This research addresses this challenge of data scarcity by leveraging parallel textline images - pairs of original Kindai text and their counterparts in contemporary Japanese fonts - to augment training datasets. We introduce a distance-based objective function that minimizes the gap between self-attention features of the parallel image pairs. Specifically, we explore Euclidean distance and Maximum Mean Discrepancy (MMD) as domain adaptation metrics. Experimental results demonstrate that our method reduces the character error rate (CER) by 2.23% and 3.94% over a Transformer-based OCR baseline when using Euclidean distance and MMD, respectively. Furthermore, our approach improves the discriminative quality of self-attention representations, leading to more effective OCR performance for historical documents.

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• TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents [50.64307290680222]
  TongGuOCR is a layout-aware and token-augmented multimodal large language model (MLLM) for OCR of Chinese historical documents.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)
• When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents [6.6457932580691015]
  Vision-Language Models (VLMs) have emerged as strong alternatives to traditional OCR systems.<n>In this work, we benchmark traditional OCR systems and VLM-based approaches on the Berrutti dataset.
  arXiv  Detail & Related papers  (2026-07-27T07:19:00Z)
• ICDAR 2026 HIPE-OCRepair Competition on LLM-Assisted OCR Post-Correction for Historical Documents [8.746127489275747]
  We present the results of HIPE-OCRepair-2026, an ICDAR competition on LLM-assisted OCR post-correction of historical documents.<n>Four teams submitted systems ranging from zero-shot prompting to continued pre-training and fine-tuning.<n>Results show that modern LLM-assisted systems can significantly improve OCR quality, but performance varies across datasets, languages, and noise levels.
  arXiv  Detail & Related papers  (2026-07-09T06:26:13Z)
• Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters [31.3410141149246]
  We introduce Chronicles-OCR, the first comprehensive benchmark specifically designed to evaluate the cross-temporal visual perception capabilities of Vision Large Language Models.<n>The dataset comprises 2,800 strictly balanced images encompassing highly diverse physical media, ranging from tortoise shells to paper-based calligraphy.<n>Chronicles-OCR formulates four rigorous quantitative tasks: cross-period character spotting, fine-grained archaic character recognition via visual referring, ancient text parsing, and script classification.
  arXiv  Detail & Related papers  (2026-05-12T11:14:25Z)
• Low-Resource Heuristics for Bahnaric Optical Character Recognition Improvement [3.2537431443459255]
  Bahnar, a minority language spoken across Vietnam, Cambodia, and Laos, faces significant preservation challenges due to limited research and data availability.<n>This study addresses the critical need for accurate digitization of Bahnar language documents through optical character recognition (OCR) technology.<n>We propose a comprehensive approach combining advanced table and non-table detection techniques with probability-based post-processings to enhance recognition accuracy.
  arXiv  Detail & Related papers  (2026-01-06T12:22:03Z)
• Reproducibility, Replicability, and Insights into Visual Document Retrieval with Late Interaction [22.41501622100226]
  Visual Document Retrieval (VDR) is an emerging research area that focuses on encoding and retrieving document images directly.<n>A recent advance in VDR was introduced by ColPali, which significantly improved retrieval effectiveness through a late interaction mechanism.<n>Our research investigates the specific contributions of late interaction by looking into query-patch matching in the context of visual document retrieval.
  arXiv  Detail & Related papers  (2025-05-12T16:37:47Z)
• 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)
• 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)
• Improving Sampling Methods for Fine-tuning SentenceBERT in Text Streams [49.3179290313959]
  This study explores the efficacy of seven text sampling methods designed to selectively fine-tune language models. We precisely assess the impact of these methods on fine-tuning the SBERT model using four different loss functions. Our findings indicate that Softmax loss and Batch All Triplets loss are particularly effective for text stream classification.
  arXiv  Detail & Related papers  (2024-03-18T23:41:52Z)
• Vision-Language Modelling For Radiological Imaging and Reports In The Low Data Regime [70.04389979779195]
  This paper explores training medical vision-language models (VLMs) where the visual and language inputs are embedded into a common space. We explore several candidate methods to improve low-data performance, including adapting generic pre-trained models to novel image and text domains. Using text-to-image retrieval as a benchmark, we evaluate the performance of these methods with variable sized training datasets of paired chest X-rays and radiological reports.
  arXiv  Detail & Related papers  (2023-03-30T18:20:00Z)
• User-Centric Evaluation of OCR Systems for Kwak'wala [92.73847703011353]
  We show that utilizing OCR reduces the time spent in the manual transcription of culturally valuable documents by over 50%. Our results demonstrate the potential benefits that OCR tools can have on downstream language documentation and revitalization efforts.
  arXiv  Detail & Related papers  (2023-02-26T21:41:15Z)
• Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing [53.89917396428747]
  Self-supervised learning in vision-language processing exploits semantic alignment between imaging and text modalities. We explicitly account for prior images and reports when available during both training and fine-tuning. Our approach, named BioViL-T, uses a CNN-Transformer hybrid multi-image encoder trained jointly with a text model.
  arXiv  Detail & Related papers  (2023-01-11T16:35:33Z)
• ALADIN: Distilling Fine-grained Alignment Scores for Efficient Image-Text Matching and Retrieval [51.588385824875886]
  Cross-modal retrieval consists in finding images related to a given query text or vice-versa. Many recent methods proposed effective solutions to the image-text matching problem, mostly using recent large vision-language (VL) Transformer networks. This paper proposes an ALign And DIstill Network (ALADIN) to fill in the gap between effectiveness and efficiency.
  arXiv  Detail & Related papers  (2022-07-29T16:01:48Z)
• Auxiliary Cross-Modal Representation Learning with Triplet Loss Functions for Online Handwriting Recognition [3.071136270246468]
  Cross-modal representation learning learns a shared embedding between two or more modalities to improve performance in a given task. We present a triplet loss with a dynamic margin for single label and sequence-to-sequence classification tasks. Our experiments show an improved classification accuracy, faster convergence, and better generalizability due to an improved cross-modal representation.
  arXiv  Detail & Related papers  (2022-02-16T07:09:04Z)
• 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)

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.