Skip to content

Latest commit

 

History

History

__base__

readme.md

Recognition Base Model

1. Introduction

This code repository contains an implementation of (CRNN:An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition)(TPAMI) and (Res-Bilstm-Attn:What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis) (ICCV 2019).

2. Preparing Dataset

Train Dataset

Dataset Samples Description Release
MJSynth 8919257 Scene text recognition synthetic data set Link
SynText 7266164 A synthesized by scene text dataset, and the text is cropped from the large image Link

Validation Dataset

Testset Instance Number Note
IIIT5K 3000 regular
SVT 647 regular
IC03_860 860 regular
IC13_857 857 regular
IC15_1811 1811 irregular
SVTP 645 irregular
CUTE80 288 irregular

Test Dataset

Testset Instance Number Note
IIIT5K 3000 regular
SVT 647 regular
IC03_860 860 regular
IC13_857 857 regular
IC15_1811 1811 irregular
SVTP 645 irregular
CUTE80 288 irregular

3. Getting Started

Preparation

A quick start is to use above lmdb-formatted datasets that contain the full benchmarks for scene text recognition tasks as belows.

Data Type: LMDB

File storage format:
   |-- train           
   |   |-- MJ
   |   |-- ST
   |-- validation
   |   |-- mixture
   |-- evaluation
   |   |-- mixture

Training

Run the following bash command in the command line,

cd .
bash ./train_script/train_att.sh 

cd .
bash ./train_script/train_crnn.sh

We provide the implementation of online validation. If you want to close it to save training time, you may modify the startup script to add --no-validate command.

Evaluation

cd .
bash ./train.sh

4. Results

Evaluation

Methods Regular Text Irregular Text Download
Name IIIT5K SVT IC03 IC13 IC15 SVTP CUTE80 Config Model
CRNN(Report) 86.2 86.0 94.4 92.6 73.6 76.0 72.2

-

-
CRNN 93.3 87.5 92.6 92.4 78.1 78.9 80.6

Config

pth [Link] (Access Code: 05IZ)
Attention(Report) 86.6 86.2 94.1 92.8 75.6 76.4 72.6

-

-
Attention 94.5 89.0 94.5 94.1 81.7 82.5 81.9

Config

pth [Link] (Access Code: r6C7)

Visualization

Here is the picture for result visualization.

visualization

Citation

@article{CRNN,
  author={Baoguang Shi and Xiang Bai and Cong Yao},
  title={An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition},
  journal={TPAMI},
  volume={39},
  number={11},
  pages={2298--2304},
  year={2017},
}

@inproceedings{Wrong,
  author={Jeonghun Baek and Geewook Kim and Junyeop Lee and Sungrae Park and Dongyoon Han and Sangdoo Yun and Seong Joon Oh and Hwalsuk Lee},
  title={What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis},
  booktitle={ICCV 2019},
  pages={4714--4722},
  publisher={{IEEE}},
  year={2019},
}

License

This project is released under the Apache 2.0 license

Contact

If there is any suggestion and problem, please feel free to contact the author with qiaoliang6@hikvision.com.