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: SCUT_DLVClab12017-06-28

Authors: Yuliang Liu, Lianwen Jin, Sheng Zhang, Canjie Luo, Zhaohai Li, Lele Xie, Zenghui Sun

Description: Two deep learning-based stages have been used, the first is to roughly detect text, and the second is to finely adjust the bounding box for accurate detection. A novel network is designed for multi-scale learning to generate tight quadrilateral proposals for the scene text. This is followed by a post-processing pipeline to improve the precision.

method: FOTS_v22018-01-22

Authors: Xuebo Liu, Ding Liang, Junjie Yan

Description: FOTS_v2 improves the performance on long text, such as Chinese.

Ranking Table

Description Paper Source Code
DateMethodAverage PrecisionPrecisionRecallHmean
2018-01-22FOTS80.16%24.28%93.99%38.59%
2017-06-28SCUT_DLVClab172.16%23.06%88.68%36.60%
2018-01-22FOTS_v271.55%22.13%93.95%35.83%
2018-05-18PSENet_NJU_ImagineLab (single-scale)17.24%20.94%80.16%33.21%
2018-07-03CLOVA-AI / PAPAGO15.94%20.64%76.58%32.51%
2017-11-09EAST++22.17%17.83%77.49%28.99%
2017-06-30TH-DL52.72%17.37%80.63%28.58%
2018-03-12ATL Cangjie OCR60.12%16.56%89.12%27.93%
2017-06-29SARI_FDU_RRPN_v161.20%15.53%87.39%26.38%
2017-06-28SARI_FDU_RRPN_v043.90%12.36%83.34%21.52%
2017-06-30Sensetime OCR60.68%5.46%93.44%10.32%
2017-06-30linkage-ER-Flow0.38%1.78%15.68%3.20%

Ranking Graphic

Ranking Graphic