method: DMText_lsvt2019-04-30
Authors: Pei Xu, Shan Huang. (Tencent)
Description: This is an instance segmentation based method. We segment the text polygons from region proposals. In the training process, We first train on images synthesized by the method of VGG-synthtext, and then fine tune on the LSVT training images. In the post-processing, we adopt NMS and filter out those polygons with low scores.
method: baseline_polygon_0.72019-04-26
Authors: Jinjin Zhang, Beihang University
Description: instance segmentation based method for text line detection by Cascade RCNN with threshold 0.7 and simplified polygon converted by mask.
method: Fudan-Supremind Detection2019-04-30
Authors: Yaowu Wei, Shangchao Su, Tairu Qiu, Xunyan Wang, Shaokang Lin, Zili Yi, Lei Deng, Mulin Xu, Jianqi Ma, Bin Li, Xiangyang Xue
Description: We propose a text segmentation algorithm based on Cascaded Mask-RCNN with deformable convolution and DenseASPP. And furthermore, we do some changes.
| Date | Method | Recall | Precision | Hmean | |||
|---|---|---|---|---|---|---|---|
| 2019-04-30 | DMText_lsvt | 80.03% | 89.28% | 84.40% | |||
| 2019-04-26 | baseline_polygon_0.7 | 80.22% | 88.99% | 84.37% | |||
| 2019-04-30 | Fudan-Supremind Detection | 81.81% | 85.94% | 83.82% | |||
| 2019-04-29 | SRCB_LSVT | 77.95% | 89.48% | 83.32% | |||
| 2019-04-30 | TMIS | 78.38% | 84.90% | 81.51% | |||
| 2019-04-26 | PSENet_v2 | 72.95% | 79.64% | 76.15% | |||
| 2020-11-23 | hrnet_w40_casecade | 72.88% | 73.51% | 73.19% | |||
| 2019-04-29 | test4 | 61.75% | 80.66% | 69.95% | |||
| 2019-04-30 | CRAFT | 64.21% | 69.52% | 66.76% | |||
| 2022-03-03 | db | 54.97% | 72.45% | 62.51% |