Skip to content
/ SSTD Public
forked from BestSonny/SSTD

Single Shot Text Detector with Regional Attention

License

Notifications You must be signed in to change notification settings

willaaam/SSTD

 
 

Repository files navigation

License

Single Shot Text Detector with Regional Attention

Introduction

SSTD is initially described in our ICCV 2017 spotlight paper.

A third-party implementation of SSTD + Focal Loss. Thanks, Ho taek Han

If you find it useful in your research, please consider citing:

@inproceedings{panhe17singleshot,
      Title   = {Single Shot Text Detector with Regional Attention},
      Author  = {He, Pan and Huang, Weilin and He, Tong and Zhu, Qile and Qiao, Yu and Li, Xiaolin},
      Note    = {Proceedings of Internatioanl Conference on Computer Vision (ICCV)},
      Year    = {2017}
      }
@inproceedings{panhe16readText,
      Title   = {Reading Scene Text in Deep Convolutional Sequences},
      Author  = {He, Pan and Huang, Weilin and Qiao, Yu and Loy, Chen Change and Tang, Xiaoou},
      Note    = {Proceedings of AAAI Conference on Artificial Intelligence, (AAAI)},
      Year    = {2016}
      }
@inproceedings{liu16ssd,
      Title   = {{SSD}: Single Shot MultiBox Detector},
      Author  = {Liu, Wei and Anguelov, Dragomir and Erhan, Dumitru and Szegedy, Christian and Reed, Scott and Fu, Cheng-Yang and Berg, Alexander C.},
      Note    = {Proceedings of European Conference on Computer Vision (ECCV)},
      Year    = {2016}
      }

Installation

  1. Get the code. We will call the directory that you cloned Caffe into $CAFFE_ROOT
git clone https://github.com/BestSonny/SSTD.git
cd SSTD
  1. Build the code. Please follow Caffe instruction to install all necessary packages and build it.
# Modify Makefile.config according to your Caffe installation.
cp Makefile.config.example Makefile.config
make -j8
# Make sure to include $CAFFE_ROOT/python to your PYTHONPATH.
make py
make test -j8
# (Optional)
make runtest -j8
# build nms
cd examples/text
make
cd ..
  1. Run the demo code. Download Model google drive, baiduyun and put it in text/model folder
cd examples
sh text/download.sh
mkdir text/result
python text/demo_test.py

About

Single Shot Text Detector with Regional Attention

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 85.1%
  • Cuda 6.5%
  • Python 4.5%
  • CMake 2.4%
  • MATLAB 0.8%
  • Makefile 0.6%
  • Shell 0.1%