Robust ReadingCompetition
Challenges

method: Amap-CVLab2018-10-29

Authors: Xinran Liu, Hang Zhang, Zhihui Hao, Wei Wang (CASIA)

Description: An instance segmentation based method. This work has been completed by Amap (AutoNavi) Computer Vision Lab, Alibaba Group in cooperation with Institute of Automation, Chinese Academy of Sciences (CASIA).

method: PKU_VDIG2018-08-08

Authors: Yudong Liu, Zheqi He, Yongtao Wang

Description: A two-stage end-to-end text detection network

method: Pixel-Anchor 2018-11-16

Authors: Yuan Li, Yuanjie Yu

Description: a novel end-to-end trainable deep neural network framework, named Pixel-Anchor, which combines semantic segmentation and SSD in one network by feature sharing and anchor-level attention mechanism to detect oriented scene text.

Ranking Table

Description Paper Source Code
DateMethodAverage PrecisionPrecisionRecallHmean
2018-10-29Amap-CVLab70.51%79.64%74.91%77.20%
2018-08-08PKU_VDIG66.74%79.82%71.77%75.58%
2018-11-16Pixel-Anchor 56.22%83.31%68.30%75.06%
2018-05-18PSENet_NJU_ImagineLab (single-scale)56.39%78.55%71.65%74.94%
2018-08-23Sogou_MM67.72%76.63%72.96%74.75%
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%
2018-07-27tongjiu50.59%70.99%71.02%71.00%
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%
2018-07-31east-IMPROVE35.06%63.37%51.19%56.63%
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