Robust ReadingCompetition
Challenges

method: FOTS2018-01-22

Authors: Xuebo Liu, Ding Liang, Shi Yan, Dagui Chen, Yu Qiao, Junjie Yan

Description: A unified end-to-end trainable Fast Oriented Text Spotting (FOTS) network for simultaneous detection and recognition, sharing computation and visual information among the two complementary tasks.

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: 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
2018-01-22FOTS49.09%49.65%66.18%56.74%
2018-10-29Amap-CVLab49.59%47.01%70.00%56.25%
2018-11-16Pixel-Anchor 32.80%50.36%62.16%55.64%
2018-01-22FOTS_v246.29%47.58%66.08%55.33%
2018-05-18PSENet_NJU_ImagineLab (single-scale)30.21%45.44%68.28%54.57%
2018-03-12ATL Cangjie OCR56.17%42.20%71.88%53.18%
2018-08-08PKU_VDIG44.88%45.28%64.17%53.09%
2017-06-28SCUT_DLVClab138.59%45.80%58.24%51.27%
2017-11-09EAST++29.75%43.27%62.30%51.07%
2018-08-23Sogou_MM44.72%40.40%66.81%50.35%
2018-07-27tongjiu22.85%36.16%64.10%46.23%
2017-06-29SARI_FDU_RRPN_v124.45%32.19%50.76%39.40%
2017-06-28SARI_FDU_RRPN_v030.92%28.94%57.72%38.55%
2018-07-31east-IMPROVE16.44%28.39%48.58%35.83%
2017-06-30TH-DL20.68%30.16%35.78%32.73%
2017-06-30Sensetime OCR44.78%17.11%68.68%27.39%
2017-06-30linkage-ER-Flow4.02%10.71%21.99%14.40%

Ranking Graphic

Ranking Graphic