method: gts-1000-minsize_13002024-03-14

Authors: w

Affiliation: n

Description: 342

method: gts-1000-th_0.42024-03-14

Authors: w

Affiliation: n

Description: 2312

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.

Ranking Table

Description Paper Source Code
DateMethodRecallPrecisionHmean
2024-03-14gts-1000-minsize_130084.41%94.51%89.17%
2024-03-14gts-1000-th_0.484.95%93.18%88.88%
2021-02-05AIX Lab., LG Electronics 88.88%88.59%88.73%
2024-03-14gts-1000-minsize_1440-th_0.483.75%92.64%87.97%
2017-07-11SRC-B-MachineLearningLab84.19%87.43%85.78%
2018-01-22FOTS80.70%89.26%84.77%
2017-06-09TextBoxes++81.79%87.72%84.65%
2017-03-20AdelaideMachineLearning79.61%90.23%84.59%
2018-03-05HoText_v180.59%88.82%84.51%
2017-01-19Yunos_Robot1.075.57%95.06%84.20%
2016-08-23HUST_MCLAB79.50%88.79%83.89%
2016-03-17Adelaide_ConvLSTMs72.52%89.50%80.12%
2016-03-10SRC-B-TextProcessingLab74.92%81.59%78.11%
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%
2015-04-02StradVision-164.99%69.46%67.15%
2015-04-02Beam search CUNI (decoding for TextSpotter - no postprocessing)52.89%59.66%56.07%
2015-05-04Baseline OpenCV 3.0 + Tesseract37.62%50.96%43.29%
2015-04-02Beam search CUNI +S (decoding for TextSpotter - spell checked)11.89%65.27%20.11%
2015-04-01Baseline-TextSpotter0.00%0.00%0.00%

Ranking Graphic