Robust ReadingCompetition
Challenges

method: CLOVA-AI / PAPAGO2018-07-03

Authors: Youngmin Baek, Bado Lee, Hwalsuk Lee

Description: Character-level text detection based on weakly-supervised learning. Multi-scale experiment result. CLOVA-AI team, Naver Corp.  (Paper in preparation)

Authors: Wenhai Wang, Xiang Li, Wenbo Hou, Tong Lu, Jian Yang

Description: A text detector based on semantic segmentation. Using only ICDAR_2017 MLT training set and ICDAR 2015 training set. Paper is in the preparation. And we will release our code latter.

method: EAST++2017-11-09

Authors: chen zhao cai

Description: this one includes some improvements over EAST(https://github.com/argman/EAST) , this one is a single scale result, but i enlarge the original image by 2X because of so many small texts.

Ranking Table

Description Paper Source Code
DateMethodAverage PrecisionPrecisionRecallHmean
2018-07-03CLOVA-AI / PAPAGO57.38%81.71%70.46%75.67%
2018-05-18PSENet_NJU_ImagineLab (single-scale)56.39%78.55%71.65%74.94%
2017-11-09EAST++56.21%78.90%69.45%73.88%
2018-03-12ATL Cangjie OCR65.19%75.47%70.76%73.04%
2018-01-22FOTS_v258.38%79.67%66.35%72.40%
2018-01-22FOTS56.40%80.01%62.47%70.16%
2017-06-28SCUT_DLVClab148.24%76.76%53.73%63.21%
2017-06-29SARI_FDU_RRPN_v151.75%68.90%56.77%62.25%
2017-06-28SARI_FDU_RRPN_v048.79%65.01%55.12%59.65%
2017-06-30Sensetime OCR60.84%48.74%70.83%57.74%
2017-06-30TH-DL29.50%62.62%33.18%43.38%
2017-06-30linkage-ER-Flow13.62%36.84%24.99%29.78%

Ranking Graphic

Ranking Graphic