Datasets Preparation¶
This page lists the datasets which are commonly used in text detection, text recognition and key information extraction, and their download links.
Text Detection¶
The structure of the text detection dataset directory is organized as follows.
├── ctw1500
│ ├── imgs
│ ├── instances_test.json
│ └── instances_training.json
├── icdar2015
│ ├── imgs
│ ├── instances_test.json
│ └── instances_training.json
├── icdar2017
│ ├── imgs
│ ├── instances_training.json
│ └── instances_val.json
├── synthtext
│ ├── imgs
│ └── instances_training.lmdb
Dataset | Images | Annotation Files | |||
---|---|---|---|---|---|
training | validation | testing | |||
CTW1500 | homepage | instances_training.json | - | instances_test.json | |
ICDAR2015 | homepage | instances_training.json | - | instances_test.json | |
ICDAR2017 | homepage | renamed_imgs | instances_training.json | instances_val.json | - |
Synthtext | homepage | instances_training.lmdb | - |
For
icdar2015
:Step1: Download
ch4_training_images.zip
andch4_test_images.zip
from homepageStep2: Download instances_training.json and instances_test.json
Step3:
mkdir icdar2015 && cd icdar2015 mv /path/to/instances_training.json . mv /path/to/instances_test.json . mkdir imgs && cd imgs ln -s /path/to/ch4_training_images training ln -s /path/to/ch4_test_images test
For
icdar2017
:To avoid the effect of rotation when load
jpg
with opencv, We provide re-savedpng
format image in renamed_images. You can copy these images toimgs
.
Text Recognition¶
The structure of the text recognition dataset directory is organized as follows.
├── mixture
│ ├── coco_text
│ │ ├── train_label.txt
│ │ ├── train_words
│ ├── icdar_2011
│ │ ├── training_label.txt
│ │ ├── Challenge1_Training_Task3_Images_GT
│ ├── icdar_2013
│ │ ├── train_label.txt
│ │ ├── test_label_1015.txt
│ │ ├── test_label_1095.txt
│ │ ├── Challenge2_Training_Task3_Images_GT
│ │ ├── Challenge2_Test_Task3_Images
│ ├── icdar_2015
│ │ ├── train_label.txt
│ │ ├── test_label.txt
│ │ ├── ch4_training_word_images_gt
│ │ ├── ch4_test_word_images_gt
│ ├── III5K
│ │ ├── train_label.txt
│ │ ├── test_label.txt
│ │ ├── train
│ │ ├── test
│ ├── ct80
│ │ ├── test_label.txt
│ │ ├── image
│ ├── svt
│ │ ├── test_label.txt
│ │ ├── image
│ ├── svtp
│ │ ├── test_label.txt
│ │ ├── image
│ ├── Syn90k
│ │ ├── shuffle_labels.txt
│ │ ├── label.txt
│ │ ├── label.lmdb
│ │ ├── mnt
│ ├── SynthText
│ │ ├── shuffle_labels.txt
│ │ ├── instances_train.txt
│ │ ├── label.txt
│ │ ├── label.lmdb
│ │ ├── synthtext
│ ├── SynthAdd
│ │ ├── label.txt
│ │ ├── label.lmdb
│ │ ├── SynthText_Add
Dataset | images | annotation file | annotation file |
---|---|---|---|
training | test | ||
coco_text | homepage | train_label.txt | - |
icdar_2011 | homepage | train_label.txt | - |
icdar_2013 | homepage | train_label.txt | test_label_1015.txt |
icdar_2015 | homepage | train_label.txt | test_label.txt |
IIIT5K | homepage | train_label.txt | test_label.txt |
ct80 | - | - | test_label.txt |
svt | homepage | - | test_label.txt |
svtp | - | - | test_label.txt |
Syn90k | homepage | shuffle_labels.txt | label.txt | - |
SynthText | homepage | shuffle_labels.txt | instances_train.txt | label.txt | - |
SynthAdd | SynthText_Add.zip (code:627x) | label.txt | - |
For
icdar_2013
:Step1: Download
Challenge2_Test_Task3_Images.zip
andChallenge2_Training_Task3_Images_GT.zip
from homepageStep2: Download test_label_1015.txt and train_label.txt
For
icdar_2015
:Step1: Download
ch4_training_word_images_gt.zip
andch4_test_word_images_gt.zip
from homepageStep2: Download train_label.txt and test_label.txt
For
IIIT5K
:Step1: Download
IIIT5K-Word_V3.0.tar.gz
from homepageStep2: Download train_label.txt and test_label.txt
For
svt
:Step1: Download
svt.zip
form homepageStep2: Download test_label.txt
Step3:
python tools/data/textrecog/svt_converter.py <download_svt_dir_path>
For
ct80
:Step1: Download test_label.txt
For
svtp
:Step1: Download test_label.txt
For
coco_text
:Step1: Download from homepage
Step2: Download train_label.txt
For
Syn90k
:Step1: Download
mjsynth.tar.gz
from homepageStep2: Download shuffle_labels.txt
Step3:
mkdir Syn90k && cd Syn90k mv /path/to/mjsynth.tar.gz . tar -xzf mjsynth.tar.gz mv /path/to/shuffle_labels.txt . # create soft link cd /path/to/mmocr/data/mixture ln -s /path/to/Syn90k Syn90k
For
SynthText
:Step1: Download
SynthText.zip
from homepageStep2: Download shuffle_labels.txt
Step3: Download instances_train.txt
Step4:
unzip SynthText.zip cd SynthText mv /path/to/shuffle_labels.txt . # create soft link cd /path/to/mmocr/data/mixture ln -s /path/to/SynthText SynthText
For
SynthAdd
:mkdir SynthAdd && cd SynthAdd mv /path/to/SynthText_Add.zip . unzip SynthText_Add.zip mv /path/to/label.txt . # create soft link cd /path/to/mmocr/data/mixture ln -s /path/to/SynthAdd SynthAdd
Note:
To convert label file with txt
format to lmdb
format,
python tools/data/utils/txt2lmdb.py -i <txt_label_path> -o <lmdb_label_path>
For example,
python tools/data/utils/txt2lmdb.py -i data/mixture/Syn90k/label.txt -o data/mixture/Syn90k/label.lmdb
Key Information Extraction¶
The structure of the key information extraction dataset directory is organized as follows.
└── wildreceipt
├── class_list.txt
├── dict.txt
├── image_files
├── test.txt
└── train.txt
Download wildreceipt.tar
Named Entity Recognition¶
CLUENER2020¶
The structure of the named entity recognition dataset directory is organized as follows.
└── cluener2020
├── cluener_predict.json
├── dev.json
├── README.md
├── test.json
├── train.json
└── vocab.txt
Download cluener_public.zip
Download vocab.txt and move
vocab.txt
tocluener2020