method: TextFuseNet (ResNet-101)2020-10-01

Authors: Jian Ye, Zhe Chen, Juhua Liu, Bo Du

Affiliation: Wuhan University

Email: leaf-yej@whu.edu.cn

Description: This is a preliminary evaluation result of TextFuseNet with ResNet-101. Multi-scale training and single-scale testing are used to get the final results. Sigma Lab, Wuhan University.

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.

method: SRCB_Art2019-04-29

Authors: Xiaobing Wang, Yi Yu, Haiyang Guo, Yingying Jiang

Description: We use RNN based adaptive representation for text detection. Given an input image, a text region proposal network is first used for extracting text proposals. Then, these proposals are verified and refined with a refinement network. Here, recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found. In this way, text regions of arbitrary shapes are detected and represented with adaptive number of boundary points. The backbone network is VGG16 with SE block used.

Besides, Mask RCNN is also used for text detection in our submission. We use the https://github.com/facebookresearch/Detectron and the backbone network is ResNext 101.

Ranking Table

Description Paper Source Code
DateMethodRecallPrecisionHmean
2020-10-01TextFuseNet (ResNet-101)72.77%85.42%78.59%
2019-04-30Fudan-Supremind Detection v371.61%79.26%75.24%
2019-04-29SRCB_Art70.30%80.41%75.02%
2019-04-30DMText_art66.15%85.09%74.43%
2019-04-25Art detect by vivo57.15%80.72%66.92%
2019-04-28Improved Progressive scale expansion Net52.24%75.88%61.88%

Ranking Graphic