Optical Character Recognition (OCR)

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

6 leaderboard tables shown for this task, 6 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

55 datasets whose archive record lists this task, ordered by the archive's paper count. 30 shown of 55 until expanded.

Subtasks archive 2025-07-28

10 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 462 papers with code (1,243 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
  21 Jul 2015 85 repositories listed Syntology ran 19 of 81 samples · 62 unverified · 17 pointer-only (licence)
  In this paper, we investigate the problem of scene text recognition, which is among the most important and challenging tasks in image-based sequence recognition.
• EAST: An Efficient and Accurate Scene Text Detector
  11 Apr 2017 31 repositories listed Syntology ran 5 of 6 samples · 1 unverified · 1 pointer-only (licence)
  Previous approaches for scene text detection have already achieved promising performances across various benchmarks.
• Shape Robust Text Detection with Progressive Scale Expansion Network
  28 Mar 2019 19 repositories listed
  Due to the fact that there are large geometrical margins among the minimal scale kernels, our method is effective to split the close text instances, making it easier to use segmentation-based methods to detect…
• Real-time Scene Text Detection with Differentiable Binarization
  20 Nov 2019 15 repositories listed Syntology ran 3 of 25 samples · 22 unverified
  Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text.
• Image-to-Markup Generation with Coarse-to-Fine Attention
  16 Sep 2016 14 repositories listed Syntology ran 1 of 13 samples · 12 unverified
  We present a neural encoder-decoder model to convert images into presentational markup based on a scalable coarse-to-fine attention mechanism.
• PP-OCR: A Practical Ultra Lightweight OCR System
  21 Sep 2020 10 repositories listed Syntology ran 0 of 12 samples · 12 unverified
  Meanwhile, several pre-trained models for the Chinese and English recognition are released, including a text detector (97K images are used), a direction classifier (600K images are used) as well as a text recognizer (17.
• PP-OCR: A Practical Ultra Lightweight OCR System
  21 Sep 2020 10 repositories listed Syntology ran 0 of 12 samples · 12 unverified
  Meanwhile, several pre-trained models for the Chinese and English recognition are released, including a text detector (97K images are used), a direction classifier (600K images are used) as well as a text recognizer (17.
• TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
  21 Sep 2021 8 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  Text recognition is a long-standing research problem for document digitalization.
• TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
  21 Sep 2021 8 repositories listed Syntology ran 0 of 6 samples · 6 unverified
  Text recognition is a long-standing research problem for document digitalization.
• Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition
  2 Nov 2018 8 repositories listed Syntology ran 0 of 8 samples · 8 unverified
  Recognizing irregular text in natural scene images is challenging due to the large variance in text appearance, such as curvature, orientation and distortion.
• A Multi-Object Rectified Attention Network for Scene Text Recognition
  10 Jan 2019 7 repositories listed
  It decreases the difficulty of recognition and enables the attention-based sequence recognition network to more easily read irregular text.
• Image-based table recognition: data, model, and evaluation
  25 Nov 2019 6 repositories listed Syntology ran 2 of 6 samples · 4 unverified
  In addition, we propose a new Tree-Edit-Distance-based Similarity (TEDS) metric for table recognition, which more appropriately captures multi-hop cell misalignment and OCR errors than the pre-established metric.
• OCR-free Document Understanding Transformer
  30 Nov 2021 5 repositories listed Syntology ran 0 of 9 samples · 9 unverified
  Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.
• OCR-free Document Understanding Transformer
  30 Nov 2021 5 repositories listed Syntology ran 0 of 9 samples · 9 unverified
  Current Visual Document Understanding (VDU) methods outsource the task of reading text to off-the-shelf Optical Character Recognition (OCR) engines and focus on the understanding task with the OCR outputs.
• Exploring Cross-Image Pixel Contrast for Semantic Segmentation
  28 Jan 2021 5 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  Inspired by the recent advance in unsupervised contrastive representation learning, we propose a pixel-wise contrastive framework for semantic segmentation in the fully supervised setting.
• Chinese Text in the Wild
  28 Feb 2018 5 repositories listed
  [python3.
• Robust Scene Text Recognition with Automatic Rectification
  12 Mar 2016 5 repositories listed
  We show that the model is able to recognize several types of irregular text, including perspective text and curved text.
• Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding
  7 Oct 2022 4 repositories listed Syntology ran 0 of 5 samples · 5 unverified
  Visually-situated language is ubiquitous -- sources range from textbooks with diagrams to web pages with images and tables, to mobile apps with buttons and forms.
• DiT: Self-supervised Pre-training for Document Image Transformer
  4 Mar 2022 4 repositories listed Syntology ran 0 of 11 samples · 11 unverified
  We leverage DiT as the backbone network in a variety of vision-based Document AI tasks, including document image classification, document layout analysis, table detection as well as text detection for OCR.
• DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement
  17 Oct 2020 4 repositories listed
  Documents often exhibit various forms of degradation, which make it hard to be read and substantially deteriorate the performance of an OCR system.
• ASTER: An Attentional Scene Text Recognizer with Flexible Rectification
  25 Jun 2018 4 repositories listed
  SCENE text recognition has attracted great interest from the academia and the industry in recent years owing to its importance in a wide range of applications.
• ASTER: An Attentional Scene Text Recognizer with Flexible Rectification
  25 Jun 2018 4 repositories listed
  SCENE text recognition has attracted great interest from the academia and the industry in recent years owing to its importance in a wide range of applications.
• NRTR: A No-Recurrence Sequence-to-Sequence Model For Scene Text Recognition
  4 Jun 2018 4 repositories listed
  Considering scene image has large variation in text and background, we further design a modality-transform block to effectively transform 2D input images to 1D sequences, combined with the encoder to extract more…
• End-to-End Interpretation of the French Street Name Signs Dataset
  13 Feb 2017 4 repositories listed
  We introduce the French Street Name Signs (FSNS) Dataset consisting of more than a million images of street name signs cropped from Google Street View images of France.
• COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
  26 Jan 2016 4 repositories listed
  The goal of COCO-Text is to advance state-of-the-art in text detection and recognition in natural images.
• COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images
  26 Jan 2016 4 repositories listed
  The goal of COCO-Text is to advance state-of-the-art in text detection and recognition in natural images.
• Scrambled text: training Language Models to correct OCR errors using synthetic data
  29 Sep 2024 3 repositories listed
  This paper shows that fine-tuning a language model on synthetic data using an LM and using a character level Markov corruption process can significantly improve the ability to correct OCR errors.
• SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning
  10 Aug 2024 3 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  With support of over 300+ LLMs and 50+ MLLMs, SWIFT stands as the open-source framework that provide the most comprehensive support for fine-tuning large models.
• SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning
  10 Aug 2024 3 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  With support of over 300+ LLMs and 50+ MLLMs, SWIFT stands as the open-source framework that provide the most comprehensive support for fine-tuning large models.
• DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction
  1 Dec 2023 3 repositories listed
  Document image dewarping is a crucial task in computer vision with numerous practical applications.

Syntology lines on 17 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.