• File
  • Strongly Contextualised results
  • Weakly Contextualised results
  • Generic results
  • Evaluation
  • End-to-End recognition
  • Word Spotting

    • 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.

    FOTS: Fast Oriented Text Spotting with a Unified Network, accepted by CVPR 2018

    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.

    Mask TextSpotter: An End-to-End TrainableNeural Network for Spotting Text with Arbitrary Shapes Minghui Liao, Pengyuan Lyu, Minghang He, Cong Yao, Wenhao Wu, Xiang Bai

    Deformable ConvNets v2: More Deformable, Better Results Xizhou Zhu, Han Hu, Stephen Lin, Jifeng Dai

    Source code

    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.

    Ranking Table

    Description Paper Source Code
    DateMethodRecallPrecisionHmean
    2018-01-22FOTS92.64%95.20%93.90%
    2021-02-05AIX Lab., LG Electronics 92.52%94.40%93.45%
    2017-07-11SRC-B-MachineLearningLab91.00%94.31%92.63%
    2016-08-23HUST_MCLAB87.38%97.02%91.95%
    2017-10-28MPTSys87.85%95.31%91.43%
    2016-03-17Adelaide_ConvLSTMs84.00%97.29%90.16%
    2016-03-10SRC-B-TextProcessingLab83.41%92.25%87.61%
    2015-10-20Deep2Text II+73.83%95.90%83.43%
    2015-04-02StradVision-178.39%87.83%82.84%
    2015-04-02Deep2Text II-272.08%83.49%77.37%
    2015-04-01Deep2Text I69.74%85.78%76.93%
    2015-04-02Beam search CUNI (decoding for TextSpotter - no postprocessing)60.98%69.51%64.97%
    2015-04-02Beam search CUNI +S (decoding for TextSpotter - spell checked)14.37%89.78%24.77%
    2015-04-01Baseline-TextSpotter0.00%0.00%0.00%

    Ranking Graphic