method: edge_link_it42018-08-09
Authors: jin ma
Description: edge_link_it4
method: StradVision2015-03-23
Authors: Hojin Cho et al.
Description: First, we extract character candidates using extremal regions (ER) Second, we verify the extracted character candidates with the character classifier trained by Agile Learning. Afterwards, we do text-patch matching which greatly enhances the recall rate, and group the characters into text regions. Finally, we apply a deep neural network for character recognition.
method: BUCT_YST2015-01-12
Authors: Wei Hu
Description: Multiple MSERs and Convolution Neural Networks are employed in our method to extract character candidates. Character candidates are then grouped by using the technique in USTB_TexStar to generate text candidates. At last, a text classifier is trained on the training dataset to verify these text candidates. The related demo of the software has been released on http://research.cs.buct.edu.cn/huwei ( or http://124.205.208.198:8081).
| Date | Method | Px. Recall | Px. Precision | Px. F-score | Well s. | Merged | Broken | Br.-Mer. | Lost | False p. | Detected | Recall | Precision | Fscore | |||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2018-08-09 | edge_link_it4 | 86.85% | 87.51% | 87.18% | 4772 | 214 | 11 | 0 | 871 | 91 | 5530 | 81.32% | 86.17% | 83.67% | |||
| 2015-03-23 | StradVision | 78.80% | 89.24% | 83.70% | 4417 | 316 | 12 | 0 | 1123 | 84 | 5076 | 75.27% | 86.96% | 80.69% | |||
| 2015-01-12 | BUCT_YST | 74.56% | 81.75% | 77.99% | 4258 | 309 | 34 | 5 | 1262 | 201 | 4998 | 72.56% | 84.37% | 78.02% | |||
| 2013-04-09 | I2R_NUS_FAR | 74.73% | 81.70% | 78.06% | 4080 | 317 | 8 | 1 | 1462 | 355 | 4998 | 69.53% | 81.49% | 75.04% | |||
| 2017-02-18 | TexFESBv11 | 60.32% | 79.93% | 68.76% | 3906 | 240 | 14 | 2 | 1706 | 259 | 4656 | 66.56% | 83.78% | 74.19% | |||
| 2013-04-08 | NSTextractor | 60.71% | 76.28% | 67.61% | 3757 | 108 | 7 | 0 | 1996 | 345 | 4450 | 64.03% | 84.36% | 72.80% | |||
| 2013-04-07 | USTB_FuStar | 69.58% | 74.45% | 71.93% | 4091 | 311 | 18 | 0 | 1448 | 966 | 5509 | 69.72% | 74.12% | 71.85% | |||
| 2013-04-08 | I2R_NUS | 73.57% | 79.04% | 76.21% | 3590 | 743 | 7 | 0 | 1528 | 357 | 4620 | 61.18% | 77.66% | 68.44% | |||
| 2013-04-08 | NSTsegmentator | 68.41% | 63.95% | 66.10% | 4046 | 156 | 18 | 0 | 1648 | 2792 | 7341 | 68.95% | 54.98% | 61.18% | |||
| 2013-04-06 | Text Detection | 64.74% | 76.20% | 70.01% | 3724 | 339 | 25 | 4 | 1776 | 1885 | 6338 | 63.46% | 57.97% | 60.59% | |||
| 2013-04-05 | OTCYMIST | 46.11% | 58.53% | 51.58% | 2547 | 361 | 34 | 0 | 2926 | 4549 | 7759 | 43.40% | 32.62% | 37.25% | |||
| 2018-04-19 | ER_flow_res32_frm58 | 86.70% | 87.72% | 87.21% | 4824 | 225 | 14 | 1 | 804 | 117 | 230 | 82.21% | 0.43% | 0.86% | |||
| 2018-04-16 | scene text segmentation and detecion with resNet32 | 87.60% | 88.40% | 88.00% | 4816 | 249 | 11 | 0 | 792 | 114 | 230 | 82.07% | 0.43% | 0.86% |