method: Sample Submission2013-03-30
Authors: Dimos
Description: Using GT as a sample submission
method: WechatOCR2021-01-30
Authors: Minhui Wu
Description: CRNN + Attention + ACE
method: TencentAILab2017-10-20
Authors: Jingchao Zhou, Hao Wang, Zhifeng Li
Description: An CNN-RNN architecture with attention mechanism for enhancement.
Description Paper Source Code
| Date | Method | Total Edit distance (case sensitive) | Correctly Recognised Words (case sensitive) | T.E.D. (case insensitive) | C.R.W. (case insensitive) | |||
|---|---|---|---|---|---|---|---|---|
| 2013-03-30 | Sample Submission | 0.0000 | 100.00% | 0.0000 | 100.00% | |||
| 2021-01-30 | WechatOCR | 9.0829 | 97.78% | 9.0829 | 97.78% | |||
| 2017-10-20 | TencentAILab | 11.4429 | 97.57% | 7.7012 | 98.26% | |||
| 2017-10-17 | Dahua OCR | 15.8606 | 97.43% | 11.1106 | 98.05% | |||
| 2017-08-22 | Tencent Youtu | 17.5148 | 96.80% | 13.6664 | 97.29% | |||
| 2019-12-18 | VARCO | 29.5695 | 95.41% | 14.7965 | 97.15% | |||
| 2020-09-02 | Huawei_GDE_AI | 42.8155 | 91.80% | 36.7162 | 93.05% | |||
| 2017-09-01 | Dahua_OCR v1 | 57.3670 | 91.31% | 42.8729 | 92.49% | |||
| 2017-07-04 | Tencent-DPPR Team & USTB-PRIR | 55.4419 | 89.58% | 39.6094 | 92.22% | |||
| 2017-02-24 | HIK_OCR | 69.2921 | 88.53% | 47.3931 | 91.04% | |||
| 2013-04-06 | PhotoOCR | 103.4071 | 82.21% | 87.1869 | 85.41% | |||
| 2013-04-05 | MAPS | 186.4451 | 80.40% | 176.6011 | 81.51% | |||
| 2013-04-05 | PLT | 187.6044 | 80.26% | 178.0789 | 81.38% | |||
| 2013-04-05 | NESP | 198.1562 | 79.29% | 181.8798 | 80.75% | |||
| 2018-04-25 | CNN+LSTM | 190.4813 | 67.27% | 164.1780 | 69.08% | |||
| 2013-05-08 | Baseline | 409.6160 | 60.95% | 400.3271 | 61.57% |