papers about ocr
No Data
some papers and datasets links collected from:
you can access the website ICDAR, and see some awesome ocr models on the "Ranking Table" of each competition's result page
there are three websites that have the dataset list of some different data type:
1 - www.iapr-tc11.org
2 - tc11.cvc.uab.es
3 - rrc.cvc.uab.es
2017 COCO-Text
2017 DeTEXT
2017 DOST
2017 FSNS
2017 MLT
2017 IEHHR
2011-2015 Born-DIgitalImage
2013-2015 Focused Scene Text
2013-2015 Text in Videos
2015 Incidental Scene Text
2017
Chinese Text in the Wild
2017
Total-Text
2017
SCUT_FORU_DB_Release
2016
SynthText in the Wild Dataset
2016
COCO-Text (Computer Vision Group, Cornell)
2016
COCO-Text API
USTB-SV1k
2014
Synthetic Word Dataset (Oxford, VGG)
2014
download
IIIT 5K-Words
2012
download
StanfordSynth(Stanford, AI Group)
2012
download
MSRA Text Detection 500 Database (MSRA-TD500)
2012
OSTD
2011
Traffice Guide Panel Text Dataset,TGPT
2016
Street View Text (SVT)
2010
KAIST Scene_Text Database
2010
Chars74k
2009
ICDAR Benchmark Datasets
|Dataset| Discription | Competition Paper | |---|---|---- |ICDAR 2015| 1000 training images and 500 testing images|
paper
paper
paper
paper
paper