Sample RankingRecallPrecisionHmean
SRC-B-MachineLearningLab100.00%83.33%90.91%
HoText_v1100.00%83.33%90.91%
Alibaba-PAI100.00%83.33%90.91%
FOTS80.00%100.00%88.89%
Tencent Youtu80.00%100.00%88.89%
Sogou_MM80.00%100.00%88.89%
Baidu VIS80.00%80.00%80.00%
Baidu VIS v280.00%80.00%80.00%
Baidu VIS v2+80.00%80.00%80.00%
NVTextSpotter80.00%80.00%80.00%
gts-swint-cocoonly-s4-3_180.00%80.00%80.00%
CPN (multi-scale)80.00%80.00%80.00%
SRC-B-TextProcessingLab60.00%100.00%75.00%
SRC-B-MachineLearningLab80.00%66.67%72.73%
Baidu IDL v360.00%75.00%66.67%
Sensetime V180.00%57.14%66.67%
Megvii-Image++60.00%60.00%60.00%
Smile60.00%60.00%60.00%
TextProposals + DictNet40.00%100.00%57.14%
e2e-mlt60.00%50.00%54.55%
e2e-mlt + bug fix60.00%50.00%54.55%
Baidu IDL60.00%42.86%50.00%
M_FOTS_Orig60.00%42.86%50.00%
Yunos_Robot1.040.00%50.00%44.44%
Deep2Text-MO20.00%50.00%28.57%
Char-level PTSD on SynthText20.00%25.00%22.22%
Baseline-TextSpotter0.00%0.00%0.00%
Beam search CUNI +S (decoding for TextSpotter - no postprocessing)0.00%0.00%0.00%
Beam search CUNI (decoding for TextSpotter - spell checked)0.00%0.00%0.00%
Baseline OpenCV3.0 + Tesseract0.00%0.00%0.00%