0

E2E-MLT

E2E-MLT -- 用于多语言场景文本的不受约束的端到端方法。「E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text」

Github repo
Main metrics

Github stars Tracking Chart

E2E-MLT

E2E-MLT -- 用于多语言场景文本的不受约束的端到端方法，代码库为：https://arxiv.org/abs/1801.09919

@@inproceedings{buvsta2018e2e,
  title={E2E-MLT-an unconstrained end-to-end method for multi-language scene text},
  author={Bu{\v{s}}ta, Michal and Patel, Yash and Matas, Jiri},
  booktitle={Asian Conference on Computer Vision},
  pages={127--143},
  year={2018},
  organization={Springer}
}

要求

预训练模型

e2e-mlt, e2e-mlt-rctw 

wget http://ptak.felk.cvut.cz/public_datasets/SyntText/e2e-mlt.h5

运行演示 

python3 demo.py -model=e2e-mlt.h5

数据

MLT SynthSet

合成文本是使用“Synthetic Data for Text Localisation in Natural Images（用于自然图像中文本本地化的合成数据）”生成的，对阿拉伯语和孟加拉语脚本渲染进行了较小的更改。

我们发现有用的东西：

训练 

python3 train.py -train_list=sample_train_data/MLT/trainMLT.txt -batch_size=8 -num_readers=5 -debug=0 -input_size=512 -ocr_batch_size=256 -ocr_feed_list=sample_train_data/MLT_CROPS/gt.txt

致谢

代码从 EAST 和 DeepTextSpotter 借用。


（The first version translated by vz on 2020.08.05）

Main metrics

Overview
Name With OwnerMichalBusta/E2E-MLT
Primary LanguageC++
Program languagePython (Language Count: 6)
PlatformLinux, Mac, Windows
License:MIT License
所有者活动
Created At2018-10-16 13:12:19
Pushed At2025-01-08 09:27:36
Last Commit At2022-08-20 10:15:29
Release Count0
用户参与
Stargazers Count292
Watchers Count15
Fork Count84
Commits Count39
Has Issues Enabled
Issues Count76
Issue Open Count31
Pull Requests Count3
Pull Requests Open Count0
Pull Requests Close Count0
项目设置
Has Wiki Enabled
Is Archived
Is Fork
Is Locked
Is Mirror
Is Private

E2E-MLT

E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text
code base for: https://arxiv.org/abs/1801.09919

@@inproceedings{buvsta2018e2e,
  title={E2E-MLT-an unconstrained end-to-end method for multi-language scene text},
  author={Bu{\v{s}}ta, Michal and Patel, Yash and Matas, Jiri},
  booktitle={Asian Conference on Computer Vision},
  pages={127--143},
  year={2018},
  organization={Springer}
}

Requirements

Pretrained Models

e2e-mlt, e2e-mlt-rctw

wget http://ptak.felk.cvut.cz/public_datasets/SyntText/e2e-mlt.h5

Running Demo

python3 demo.py -model=e2e-mlt.h5

Data

MLT SynthSet

Synthetic text has been generated using Synthetic Data for Text Localisation in Natural Images, with minor changes for Arabic and Bangla script rendering.

What we have found useful:

  • for generating Arabic Scene Text: https://github.com/mpcabd/python-arabic-reshaper
  • for generating Bangla Scene Text: PyQt4
  • having somebody who can read non-latin scripts: we would like to thank Ali Anas for reviewing generated Arabic scene text.

Training

python3 train.py -train_list=sample_train_data/MLT/trainMLT.txt -batch_size=8 -num_readers=5 -debug=0 -input_size=512 -ocr_batch_size=256 -ocr_feed_list=sample_train_data/MLT_CROPS/gt.txt

Acknowledgments

Code borrows from EAST and DeepTextSpotter