ICDAR 2013

Introduced by Dimosthenis Karatzas et al. in ICDAR 2013 Robust Reading Competition

The ICDAR 2013 dataset consists of 229 training images and 233 testing images, with word-level annotations provided. It is the standard benchmark dataset for evaluating near-horizontal text detection.

Source: Single Shot Text Detector with Regional Attention

Homepage

Benchmarks

Add a new result Link an existing benchmark

Task	Dataset Variant	Best Model
Scene Text Recognition	ICDAR2013	CLIP4STR-L*
Scene Text Detection	ICDAR 2013	TextFuseNet
Table Detection	ICDAR2013	cascadetabnet

Papers

Paper	Code	Results	Date	Stars

Dataset Loaders

Add Remove

activeloopai/Hub

7,698

mindee/doctr

3,029

tanglang96/DataLoaders_DALI

876

Tasks

Scene Text Recognition
Scene Text Detection
Table Detection

Handwritten Chinese Text Recognition

Similar Datasets

MSRA-TD500

ICDAR 2015

SVT

ICDAR 2003

Source: https://plos.figshare.com/articles/Detection_examples_of_the_proposed_method_on_the_ICDAR_2013_dataset_17_/5325856.

Usage

License

Unknown

Modalities

Images
Texts

Languages

English

ICDAR 2013

Benchmarks Edit Add a new result Link an existing benchmark