Inactive evaluations
method: Alibaba-PAI2019-02-01
Authors: Alibaba-PAI OCR team
Description: A end-to-end text spotter by Alibaba-PAI OCR team.
method: Sogou_MM2018-11-02
Authors: Baojun Li, Tao Wei, Qian Wang, Bin Li
Description: An End-to-End Text Spotter with Global Concatenating Feature Enhancement.
method: Baidu VIS v2+2018-08-01
Authors: VIS-OCR
Description: An improved end-to-end text localization and recognition result submitted by Baidu VIS-OCR.
Description Paper Source Code
| Date | Method | Recall | Precision | Hmean | |||
|---|---|---|---|---|---|---|---|
| 2019-02-01 | Alibaba-PAI | 78.48% | 91.11% | 84.32% | |||
| 2018-11-02 | Sogou_MM | 80.45% | 86.67% | 83.45% | |||
| 2018-08-01 | Baidu VIS v2+ | 78.38% | 85.86% | 81.95% | |||
| 2018-07-30 | Tencent Youtu | 77.13% | 87.16% | 81.84% | |||
| 2018-07-02 | Baidu VIS v2 | 77.47% | 86.13% | 81.57% | |||
| 2024-02-26 | gts-swint-cocoonly-s4-3_1 | 77.56% | 84.57% | 80.91% | |||
| 2018-03-05 | HoText_v1 | 76.17% | 85.75% | 80.67% | |||
| 2017-10-23 | Baidu VIS | 72.27% | 90.10% | 80.20% | |||
| 2018-01-22 | FOTS | 69.91% | 91.09% | 79.11% | |||
| 2017-08-02 | Sensetime V1 | 70.97% | 89.01% | 78.97% | |||
| 2018-03-28 | SRC-B-MachineLearningLab | 70.68% | 89.46% | 78.97% | |||
| 2017-07-17 | Baidu IDL v3 | 69.23% | 86.21% | 76.80% | |||
| 2022-04-21 | NVTextSpotter | 70.82% | 79.73% | 75.01% | |||
| 2017-07-12 | SRC-B-MachineLearningLab | 64.52% | 81.06% | 71.85% | |||
| 2016-07-21 | Baidu IDL | 58.83% | 64.15% | 61.38% | |||
| 2019-04-11 | e2e-mlt + bug fix | 55.71% | 58.49% | 57.07% | |||
| 2018-10-25 | e2e-mlt | 49.45% | 55.13% | 52.13% | |||
| 2016-04-05 | SRC-B-TextProcessingLab | 38.57% | 71.84% | 50.19% | |||
| 2016-03-02 | TextProposals + DictNet | 36.69% | 76.58% | 49.61% | |||
| 2016-10-20 | Yunos_Robot1.0 | 36.30% | 67.81% | 47.29% | |||
| 2015-11-09 | Megvii-Image++ | 33.70% | 49.19% | 40.00% | |||
| 2021-02-11 | M_FOTS_Orig | 32.50% | 35.81% | 34.07% | |||
| 2021-05-25 | Char-level PTSD on SynthText | 18.73% | 33.19% | 23.95% | |||
| 2015-04-02 | Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 14.01% | 33.72% | 19.80% | |||
| 2015-04-02 | Deep2Text-MO | 13.82% | 21.34% | 16.77% | |||
| 2015-05-04 | Baseline OpenCV3.0 + Tesseract | 7.37% | 32.48% | 12.01% | |||
| 2015-04-02 | Beam search CUNI (decoding for TextSpotter - spell checked) | 5.92% | 64.74% | 10.85% | |||
| 2015-04-02 | Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |