Inactive evaluations
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.
method: Alibaba-PAI2019-02-01
Authors: Alibaba-PAI OCR team
Description: A end-to-end text spotter by Alibaba-PAI OCR team.
Description Paper Source Code
| Date | Method | Recall | Precision | Hmean | |||
|---|---|---|---|---|---|---|---|
| 2018-11-02 | Sogou_MM | 89.17% | 93.87% | 91.46% | |||
| 2018-08-01 | Baidu VIS v2+ | 87.84% | 93.48% | 90.57% | |||
| 2019-02-01 | Alibaba-PAI | 85.34% | 95.32% | 90.06% | |||
| 2018-07-30 | Tencent Youtu | 85.75% | 93.80% | 89.59% | |||
| 2018-07-02 | Baidu VIS v2 | 87.49% | 91.56% | 89.48% | |||
| 2018-03-05 | HoText_v1 | 85.14% | 93.39% | 89.07% | |||
| 2024-02-26 | gts-swint-cocoonly-s4-3_1 | 81.97% | 94.69% | 87.87% | |||
| 2018-03-28 | SRC-B-MachineLearningLab | 80.64% | 96.05% | 87.67% | |||
| 2018-01-22 | FOTS | 80.03% | 95.32% | 87.01% | |||
| 2017-10-23 | Baidu VIS | 80.90% | 93.62% | 86.79% | |||
| 2017-08-02 | Sensetime V1 | 78.75% | 96.25% | 86.63% | |||
| 2017-07-17 | Baidu IDL v3 | 75.13% | 92.34% | 82.85% | |||
| 2018-07-25 | Smile | 71.14% | 94.50% | 81.18% | |||
| 2017-07-12 | SRC-B-MachineLearningLab | 71.65% | 92.00% | 80.56% | |||
| 2022-04-21 | NVTextSpotter | 71.14% | 80.20% | 75.40% | |||
| 2016-12-26 | HUST_MCLAB | 55.16% | 97.91% | 70.57% | |||
| 2016-07-21 | Baidu IDL | 62.82% | 69.02% | 65.78% | |||
| 2019-04-28 | DIY FOTS | 58.22% | 61.49% | 59.81% | |||
| 2019-04-11 | e2e-mlt + bug fix | 55.46% | 57.55% | 56.49% | |||
| 2016-03-02 | TextProposals + DictNet | 40.50% | 90.73% | 56.00% | |||
| 2016-04-05 | SRC-B-TextProcessingLab | 41.42% | 77.91% | 54.08% | |||
| 2018-10-25 | e2e-mlt | 49.34% | 54.55% | 51.81% | |||
| 2015-11-09 | Megvii-Image++ | 42.29% | 61.02% | 49.95% | |||
| 2016-10-20 | Yunos_Robot1.0 | 38.30% | 69.83% | 49.47% | |||
| 2015-04-03 | Stradvision-2 | 34.22% | 69.57% | 45.87% | |||
| 2021-02-11 | M_FOTS_Orig | 33.30% | 36.36% | 34.76% | |||
| 2015-04-02 | StradVision_v1 | 42.24% | 29.37% | 34.65% | |||
| 2015-04-01 | NJU Text (Version3) | 25.69% | 50.71% | 34.10% | |||
| 2021-05-25 | Char-level PTSD on SynthText | 19.05% | 33.33% | 24.24% | |||
| 2015-04-02 | Beam search CUNI +S (decoding for TextSpotter - no postprocessing) | 16.60% | 39.49% | 23.37% | |||
| 2015-04-02 | Deep2Text-MO | 14.61% | 22.08% | 17.58% | |||
| 2015-05-04 | Baseline OpenCV3.0 + Tesseract | 8.89% | 41.63% | 14.65% | |||
| 2015-04-02 | Beam search CUNI (decoding for TextSpotter - spell checked) | 7.66% | 81.97% | 14.01% | |||
| 2015-04-02 | Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |