Restoration-Guided Kuzushiji Character Recognition Framework under Seal Interference

• URL: http://arxiv.org/abs/2602.19086v1
• Date: Sun, 22 Feb 2026 07:58:29 GMT
• Title: Restoration-Guided Kuzushiji Character Recognition Framework under Seal Interference
• Abstract summary: Kuzushiji was one of the most popular writing styles in pre-modern Japan and was widely used in both personal letters and official documents.<n>Recent research has focused on developing automated Kuzushiji character recognition methods.<n>However, existing methods struggle to maintain recognition accuracy under seal interference.
• Score: 4.045683514325492
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Kuzushiji was one of the most popular writing styles in pre-modern Japan and was widely used in both personal letters and official documents. However, due to its highly cursive forms and extensive glyph variations, most modern Japanese readers cannot directly interpret Kuzushiji characters. Therefore, recent research has focused on developing automated Kuzushiji character recognition methods, which have achieved satisfactory performance on relatively clean Kuzushiji document images. However, existing methods struggle to maintain recognition accuracy under seal interference (e.g., when seals overlap characters), despite the frequent occurrence of seals in pre-modern Japanese documents. To address this challenge, we propose a three-stage restoration-guided Kuzushiji character recognition (RG-KCR) framework specifically designed to mitigate seal interference. We construct datasets for evaluating Kuzushiji character detection (Stage 1) and classification (Stage 3). Experimental results show that the YOLOv12-medium model achieves a precision of 98.0% and a recall of 93.3% on the constructed test set. We quantitatively evaluate the restoration performance of Stage 2 using PSNR and SSIM. In addition, we conduct an ablation study to demonstrate that Stage 2 improves the Top-1 accuracy of Metom, a Vision Transformer (ViT)-based Kuzushiji classifier employed in Stage 3, from 93.45% to 95.33%. The implementation code of this work is available at https://ruiyangju.github.io/RG-KCR.

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• TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents [50.64307290680222]
  TongGuOCR is a layout-aware and token-augmented multimodal large language model (MLLM) for OCR of Chinese historical documents.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)
• DKDS: A Benchmark Dataset of Degraded Kuzushiji Documents with Seals for Detection and Binarization [4.045683514325492]
  Kuzushiji, a pre-modern Japanese cursive script, can currently be read and understood by only a few thousand trained experts in Japan.<n>Current Optical Character Recognition techniques fail to consider various types of noise, such as document degradation and seals.<n>We introduce the Degraded Kuzushiji Documents with Seals dataset as a new benchmark for related tasks.
  arXiv  Detail & Related papers  (2025-11-12T08:45:22Z)
• Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric [76.66966098297986]
  We present 3DGS-QA, the first subjective quality assessment dataset for 3DGS.<n>It comprises 225 degraded reconstructions across 15 object types, enabling a controlled investigation of common distortion factors.<n>Our model extracts spatial and photometric cues from the Gaussian representation to estimate perceived quality in a structure-aware manner.
  arXiv  Detail & Related papers  (2025-11-11T09:34:20Z)
• Training Kindai OCR with parallel textline images and self-attention feature distance-based loss [0.6767885381740952]
  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.
  arXiv  Detail & Related papers  (2025-08-12T01:01:32Z)
• The \textit{Questio de aqua et terra}: A Computational Authorship Verification Study [49.56191463229252]
  This study investigates the authenticity of the Questio via computational authorship verification (AV)<n>We build a family of AV systems and assemble a corpus of 330 13th- and 14th-century Latin texts.<n>The application of the AV system to the Questio returns a highly confident prediction concerning its authenticity.
  arXiv  Detail & Related papers  (2025-01-07T18:42:05Z)
• MOODv2: Masked Image Modeling for Out-of-Distribution Detection [57.17163962383442]
  This study explores distinct pretraining tasks and employing various OOD score functions. Our framework, MOODv2, impressively enhances 14.30% AUROC to 95.68% on ImageNet and achieves 99.98% on CIFAR-10.
  arXiv  Detail & Related papers  (2024-01-05T02:57:58Z)
• DocTER: Evaluating Document-based Knowledge Editing [53.14000724633775]
  We explore knowledge editing using easily accessible documents instead of manually labeled factual triples.<n>A comprehensive four-perspective evaluation is introduced: Edit Success, Locality, Reasoning, and Cross-lingual Transfer.<n>Experiments on popular knowledge editing methods demonstrate that editing with documents presents significantly greater challenges than using triples.
  arXiv  Detail & Related papers  (2023-08-19T09:17:19Z)
• Noisy-Correspondence Learning for Text-to-Image Person Re-identification [50.07634676709067]
  We propose a novel Robust Dual Embedding method (RDE) to learn robust visual-semantic associations even with noisy correspondences. Our method achieves state-of-the-art results both with and without synthetic noisy correspondences on three datasets.
  arXiv  Detail & Related papers  (2023-08-19T05:34:13Z)
• Lenient Evaluation of Japanese Speech Recognition: Modeling Naturally Occurring Spelling Inconsistency [8.888638284299736]
  We create a lattice of plausible respellings of the reference transcription using a combination of lexical resources, a Japanese text-processing system, and a neural machine translation model. Our method, which does not penalize the system for choosing a valid alternate spelling of a word, affords a 2.4%-3.1% absolute reduction in CER depending on the task.
  arXiv  Detail & Related papers  (2023-06-07T15:39:02Z)
• Predicting the Ordering of Characters in Japanese Historical Documents [6.82324732276004]
  Change in Japanese writing system in 1900 made historical documents inaccessible for the general public. We explore a few approaches to the task of predicting the sequential ordering of the characters. Our best-performing system has an accuracy of 98.65% and has a perfect accuracy on 49% of the books in our dataset.
  arXiv  Detail & Related papers  (2021-06-12T14:39:20Z)
• Self-supervised Deep Reconstruction of Mixed Strip-shredded Text Documents [63.41717168981103]
  This work extends our previous deep learning method for single-page reconstruction to a more realistic/complex scenario. In our approach, the compatibility evaluation is modeled as a two-class (valid or invalid) pattern recognition problem. The proposed method outperforms the competing ones on complex scenarios, achieving accuracy superior to 90%.
  arXiv  Detail & Related papers  (2020-07-01T21:48:05Z)
• Automated Transcription for Pre-Modern Japanese Kuzushiji Documents by Random Lines Erasure and Curriculum Learning [6.700873164609009]
  Most of the previous methods divided the recognition process into character segmentation and recognition. In this paper, we enlarge our previous humaninspired recognition system from multiple lines to the full-page of Kuzushiji documents. For the lack of training data, we propose a random text line erasure approach that randomly erases text lines and distorts documents.
  arXiv  Detail & Related papers  (2020-05-06T09:17:28Z)

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.