• Stars
    star
    110
  • Rank 314,963 (Top 7 %)
  • Language
    Python
  • License
    MIT License
  • Created about 3 years ago
  • Updated about 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection; Accepted by ICCV2021;The paper at: http://arxiv.org/abs/2107.12664

TextBPN

Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection; Accepted by ICCV2021.

The codes and paper of TextBPN++ have been released at:TextBPN-Puls-Plus.

NOTE:TextBPN++ contained the code of TextBPN,so it is recommended to refer to code in TextBPN-Puls-Plus.

1.Prerequisites

python 3.9;
PyTorch 1.7.0;
Numpy >=1.2.0
CUDA 11.1;
GCC >=10.0;
opencv-python < 4.5.0
NVIDIA GPU(with 11G or larger GPU memory for inference);

2.Dataset Links

  1. CTW1500
  2. TD500
  3. Total-Text

NOTE: The images of each dataset can be obtained from their official website.

3.Models

4.Running Evaluation

run:

sh eval.sh

The details are as follows:

#!/bin/bash
##################### Total-Text ###################################
# test_size=[640,1024]--cfglib/option
CUDA_LAUNCH_BLOCKING=1 python eval_textBPN.py --exp_name Totaltext --checkepoch 390 --dis_threshold 0.3 --cls_threshold 0.825 --test_size 640 1024 --gpu 1

###################### CTW-1500 ####################################
# test_size=[640,1024]--cfglib/option
# CUDA_LAUNCH_BLOCKING=1 python eval_textBPN.py --exp_name Ctw1500 --checkepoch 560 --dis_threshold 0.3 --cls_threshold 0.8 --test_size 640 1024 --gpu 1

#################### MSRA-TD500 ######################################
# test_size=[640,1024]--cfglib/option
#CUDA_LAUNCH_BLOCKING=1 python eval_textBPN.py --exp_name TD500 --checkepoch 680 --dis_threshold 0.3 --cls_threshold 0.925 --test_size 640 1024 --gpu 1

5.Experiments results

Citing the related works

Please cite the related works in your publications if it helps your research:

  @inproceedings{DBLP:conf/iccv/Zhang0YWY21,
  author    = {Shi{-}Xue Zhang and
               Xiaobin Zhu and
               Chun Yang and
               Hongfa Wang and
               Xu{-}Cheng Yin},
  title     = {Adaptive Boundary Proposal Network for Arbitrary Shape Text Detection},
  booktitle = {2021 {IEEE/CVF} International Conference on Computer Vision, {ICCV} 2021, Montreal, QC, Canada, October 10-17, 2021},
  pages     = {1285--1294},
  publisher = {{IEEE}},
  year      = {2021},
}

@article{zhang2023arbitrary,
  title={Arbitrary shape text detection via boundary transformer},
  author={Zhang, Shi-Xue and Yang, Chun and Zhu, Xiaobin and Yin, Xu-Cheng},
  journal={IEEE Transactions on Multimedia},
  year={2023},
  publisher={IEEE}
}

License

This project is licensed under the MIT License - see the LICENSE.md file for details

More Repositories

1

DRRG

Deep relational reasoning graph network for arbitrary shape text detection; Accepted by CVPR 2020 (Oral). http://arxiv.org/abs/2003.07493
C++
269
star
2

TextBPN-Plus-Plus

Arbitrary Shape Text Detection via Boundary Transformer;The paper at: https://arxiv.org/abs/2205.05320, which has been accepted by IEEE Transactions on Multimedia (T-MM 2023).
Python
162
star
3

TextPMs

Arbitrary Shape Text Detection via Segmentation with Probability Maps; accepted by TPAMI2022
C++
94
star
4

GHM_Loss

The tensorflow implementation of GHM loss include class loss and regression loss. GHM loss is peoposed in "Gradient Harmonized Single-stage Detector" published on AAAI 2019 (Oral).
Python
64
star
5

OHEM-loss

tensorflow implementation of OHEM loss and Support the sigmoid or softmax entropy loss
Python
31
star
6

GloRe

Tensorflow implementation of Global Reasoning unit (GloRe) from Graph-Based Global Reasoning Networks. GCN Network Blok
Python
28
star
7

Focal-loss

The code is tensorflow implement for focal loss for Dense Object Detection. https://arxiv.org/abs/1708.02002
Python
20
star
8

AnalysisEEG

2020年研究生数学建模竞赛C题-脑电波分析(代码及数据)
Python
7
star
9

TaggingTool

An annotation tool for target detection and text detection, which supports both image and video media files and only supports Windows system environment. labelMe, Tagging, Annotation.
C#
7
star
10

TextFormat_To_cocoJson

converting detection txt format for COCO json format
Python
4
star
11

python-Interface-Cpp

Interface python code by C++ , support python3
Makefile
2
star
12

GXYM.github.io

HTML
1
star