Inactive evaluations
method: Baidu VIS v22018-07-02
Authors: VIS-OCR
Description: An end-to-end text localization and recognition result submitted by Baidu VIS-OCR, the former OCR team at Baidu IDL.
method: SRC-B-MachineLearningLab2018-03-28
Authors: Xiaobing Wang, Yingying Jiang, Xiangyu Zhu, Yi Yu, Haiyang Guo, Hao Guo, Ning An, Zhenbo Luo
Description: Samsung R&D Institute of China - Beijing, Machine Learning Lab.
Detection is based on R2CNN.
Recognition is CNN-LSTM based method.
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.
Description Paper Source Code
| Date | Method | Recall | Precision | Hmean | |||
|---|---|---|---|---|---|---|---|
| 2018-07-02 | Baidu VIS v2 | 83.44% | 89.24% | 86.24% | |||
| 2018-03-28 | SRC-B-MachineLearningLab | 75.54% | 95.21% | 84.24% | |||
| 2018-01-22 | FOTS | 75.45% | 93.61% | 83.55% | |||
| 2017-07-12 | SRC-B-MachineLearningLab | 68.32% | 89.08% | 77.33% | |||
| 2016-12-26 | HUST_MCLAB | 52.00% | 97.65% | 67.86% | |||
| 2019-04-11 | e2e-mlt + bug fix | 55.71% | 58.49% | 57.07% | |||
| 2016-03-02 | TextProposals + DictNet | 37.89% | 89.84% | 53.30% | |||
| 2016-04-05 | SRC-B-TextProcessingLab | 40.11% | 76.42% | 52.60% | |||
| 2018-10-25 | e2e-mlt | 49.45% | 55.13% | 52.13% | |||
| 2015-11-09 | Megvii-Image++ | 39.38% | 57.48% | 46.74% | |||
| 2015-04-03 | Stradvision-2 | 32.21% | 67.92% | 43.70% | |||
| 2015-04-02 | StradVision_v1 | 39.77% | 28.51% | 33.21% | |||
| 2015-04-01 | NJU Text (Version3) | 24.51% | 48.80% | 32.63% | |||
| 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) | 15.65% | 37.83% | 22.14% | |||
| 2015-04-02 | Deep2Text-MO | 13.82% | 21.34% | 16.77% | |||
| 2015-04-02 | Beam search CUNI (decoding for TextSpotter - spell checked) | 7.22% | 81.08% | 13.26% | |||
| 2015-04-02 | Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |