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: FOTS_v22018-01-22

Authors: Xuebo Liu, Ding Liang, Junjie Yan

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

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.

Ranking Table

Description Paper Source Code
DateMethodAverage PrecisionPrecisionRecallHmean
2018-01-22FOTS66.08%35.14%79.56%48.75%
2018-01-22FOTS_v265.40%33.05%81.66%47.05%
2018-05-18PSENet_NJU_ImagineLab (single-scale)25.15%32.86%76.53%45.98%
2017-11-09EAST++27.79%30.80%78.34%44.21%
2017-06-28SCUT_DLVClab147.05%31.35%68.79%43.07%
2018-07-03CLOVA-AI / PAPAGO20.05%31.18%64.84%42.11%
2018-03-12ATL Cangjie OCR64.38%26.58%81.19%40.05%
2017-06-29SARI_FDU_RRPN_v151.15%22.99%71.06%34.74%
2017-06-28SARI_FDU_RRPN_v035.58%18.86%68.59%29.58%
2017-06-30TH-DL30.05%20.54%49.94%29.11%
2017-06-30Sensetime OCR47.00%9.03%80.09%16.23%
2017-06-30linkage-ER-Flow0.99%2.95%13.05%4.81%

Ranking Graphic

Ranking Graphic