Inactive evaluations
method: AIX Lab., LG Electronics 2021-02-05
Authors: Wonju Lee and Joseph Lim
Affiliation: AI Lab., Future Tech. Center, CTO, LG Electronics
Email: wonju2.lee@lge.com
Description: We reimplemented the end-to-end text spotting method combined the Mask TextSpotter with Deformable ConvNets. We tried to pre-train synthText images for character-level annotations and to fine-tune real world images like following papers for the generalization. We don't use any private data.
method: TencentAILab2017-10-28
Authors: Jingchao Zhou, Xing Ji, Zheng Zhou, Zhifeng Li
Description: Our method consists of two networks: text detection network employed in task 2.1 and word recognition network employed in task 2.2. Two networks are integrated with cascade training to achieve superior performance.
method: gts-1000-th_0.42024-03-14
Authors: w
Affiliation: n
Description: 2312
Description Paper Source Code
| Date | Method | Recall | Precision | Hmean | |||
|---|---|---|---|---|---|---|---|
| 2021-02-05 | AIX Lab., LG Electronics | 93.02% | 97.93% | 95.41% | |||
| 2017-10-28 | TencentAILab | 95.75% | 94.41% | 95.07% | |||
| 2024-03-14 | gts-1000-th_0.4 | 87.90% | 99.02% | 93.13% | |||
| 2017-06-09 | TextBoxes++ | 89.64% | 96.59% | 92.99% | |||
| 2024-03-14 | gts-1000-minsize_1300 | 87.24% | 99.13% | 92.81% | |||
| 2024-03-14 | gts-1000-minsize_1440-th_0.4 | 86.91% | 98.64% | 92.41% | |||
| 2017-07-11 | SRC-B-MachineLearningLab | 89.75% | 94.49% | 92.06% | |||
| 2018-01-22 | FOTS | 88.33% | 95.97% | 91.99% | |||
| 2016-08-23 | HUST_MCLAB | 87.68% | 95.83% | 91.57% | |||
| 2017-03-20 | AdelaideMachineLearning | 86.70% | 95.78% | 91.01% | |||
| 2020-10-30 | MaskTextSpotter | 85.82% | 95.28% | 90.30% | |||
| 2018-03-05 | HoText_v1 | 85.39% | 95.72% | 90.26% | |||
| 2017-10-28 | MPTSys | 84.08% | 96.13% | 89.70% | |||
| 2016-03-17 | Adelaide_ConvLSTMs | 79.39% | 96.68% | 87.19% | |||
| 2016-03-10 | SRC-B-TextProcessingLab | 81.68% | 93.16% | 87.04% | |||
| 2015-04-03 | VGGMaxBBNet_095 | 82.12% | 91.05% | 86.35% | |||
| 2015-04-03 | VGGMaxBBNet (055) | 82.99% | 89.63% | 86.18% | |||
| 2017-01-19 | Yunos_Robot1.0 | 75.57% | 95.06% | 84.20% | |||
| 2015-10-20 | Deep2Text II+ | 72.08% | 94.56% | 81.81% | |||
| 2015-04-02 | StradVision-1 | 75.03% | 88.66% | 81.28% | |||
| 2015-04-02 | Deep2Text II-2 | 69.79% | 81.74% | 75.29% | |||
| 2015-04-01 | NJU Text (Version3) | 69.47% | 80.13% | 74.42% | |||
| 2015-04-01 | Deep2Text I | 66.74% | 83.95% | 74.36% | |||
| 2015-04-02 | MSER MRF | 61.40% | 84.53% | 71.13% | |||
| 2015-04-02 | Beam search CUNI (decoding for TextSpotter - no postprocessing) | 58.89% | 68.01% | 63.12% | |||
| 2015-05-04 | Baseline OpenCV 3.0 + Tesseract | 48.96% | 75.72% | 59.47% | |||
| 2015-04-02 | Beam search CUNI +S (decoding for TextSpotter - spell checked) | 15.27% | 92.72% | 26.22% | |||
| 2015-04-01 | Baseline-TextSpotter | 0.00% | 0.00% | 0.00% |