method: AIX Lab., LG Electronics 2021-02-05

Authors: Wonju Lee and Joseph Lim

Affiliation: AI Lab., Future Tech. Center, CTO, LG Electronics


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: SRC-B-MachineLearningLab2017-07-11

Authors: Shuli Yang, Yingying Jiang, Xiaobing Wang, Xiangyu Zhu, Pei Fu, Hua Wang, Zhenbo Luo

Description: Samsung R&D Institute of China - Beijing. Machine Learning Lab. Our method is based on 2.1 and 2.3 (updated version). The paper is in preparation.

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.

Ranking Table

Description Paper Source Code
2021-02-05AIX Lab., LG Electronics 88.88%88.59%88.73%
2015-10-20Deep2Text II+69.68%86.00%76.99%
2015-04-02Deep2Text II-269.79%81.74%75.29%
2015-04-01Deep2Text I66.74%83.95%74.36%
2015-04-02Beam search CUNI (decoding for TextSpotter - no postprocessing)52.89%59.66%56.07%
2015-04-02Beam search CUNI +S (decoding for TextSpotter - spell checked)11.89%65.27%20.11%

Ranking Graphic