</> Code with Papers by Syntology

Datasets › ICDAR 2003

ICDAR 2003

Introduced in ICDAR 2003 Robust Reading Competitions1 Jan 2003 archive 2025-07-28

The ICDAR2003 dataset is a dataset for scene text recognition. It contains 507 natural scene images (including 258 training images and 249 test images) in total. The images are annotated at character level. Characters and words can be cropped from the images.

Source: Robust Scene Text Recognition Using Sparse Coding based Features Image Source: https://www.researchgate.net/figure/The-results-of-text-localization-and-extraction-on-ICDAR-2003-dataset_fig3_290070044

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 1 leaderboard whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Scene Text Recognition ICDAR 2003 Yet Another Text Recognizer Accuracy 97.1 Why You Should Try the Real Data for the Scene Text Recognition openvinotoolkit/training_extensions 12 Compare

Papers archive 2025-07-28

12 shown of 12 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 53. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Self-supervised Implicit Glyph Attention for Text Recognition 1 1 7 Mar 2022 not harvested
SAFL: A Self-Attention Scene Text Recognizer with Focal Loss 1 1 1 Jan 2022 not harvested
Why You Should Try the Real Data for the Scene Text Recognition 1 1 29 Jul 2021 not harvested
Vision Transformer for Fast and Efficient Scene Text Recognition 3 1 18 May 2021 not harvested
Revisiting Classification Perspective on Scene Text Recognition 1 1 22 Feb 2021 not harvested
Decoupled Attention Network for Text Recognition 5 1 21 Dec 2019 not harvested
On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention 2 1 10 Oct 2019 not harvested
What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis 13 1 3 Apr 2019 ran 0 of 19 samples (19 unverified)
AON: Towards Arbitrarily-Oriented Text Recognition 1 1 12 Nov 2017 not harvested
Star-net: A spatial attention residue network for scene text recognition. 1 1 20 Sep 2016 not harvested
Robust Scene Text Recognition with Automatic Rectification 5 1 12 Mar 2016 not harvested
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition 85 1 21 Jul 2015 ran 19 of 81 samples (62 unverified; 17 pointer-only for licence)

Dataset loaders archive 2025-07-28

mindee.github.io/doctr/latest/datasets.html#doctr.datasets.IC03mindee/doctrtfpytorch

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Optical Character Recognition (OCR)Scene Text Recognition

License archive 2025-07-28

Custom (research-only)

Modalities archive 2025-07-28

Images

Languages archive 2025-07-28

English

Variants archive 2025-07-28

  • ICDAR 2003

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections