README.md 7.9 KB
Newer Older
littletomatodonkey's avatar
littletomatodonkey 已提交
1
English | [简体中文](README_ch.md)
W
weishengyu 已提交
2

littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
3 4
## Style Text

littletomatodonkey's avatar
littletomatodonkey 已提交
5 6 7
### Contents
- [1. Introduction](#Introduction)
- [2. Preparation](#Preparation)
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
8 9
- [3. Quick Start](#Quick_Start)
- [4. Applications](#Applications)
littletomatodonkey's avatar
littletomatodonkey 已提交
10
- [5. Code Structure](#Code_structure)
W
weishengyu 已提交
11 12


littletomatodonkey's avatar
littletomatodonkey 已提交
13 14
<a name="Introduction"></a>
### Introduction
W
weishengyu 已提交
15

littletomatodonkey's avatar
littletomatodonkey 已提交
16 17 18 19 20
<div align="center">
    <img src="doc/images/3.png" width="800">
</div>

<div align="center">
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
21
    <img src="doc/images/9.png" width="600">
littletomatodonkey's avatar
littletomatodonkey 已提交
22 23 24 25 26 27 28 29 30 31
</div>


The Style-Text data synthesis tool is a tool based on Baidu's self-developed text editing algorithm "Editing Text in the Wild" [https://arxiv.org/abs/1908.03047](https://arxiv.org/abs/1908.03047).

Different from the commonly used GAN-based data synthesis tools, the main framework of Style-Text includes:
* (1) Text foreground style transfer module.
* (2) Background extraction module.
* (3) Fusion module.

littletomatodonkey's avatar
littletomatodonkey 已提交
32
After these three steps, you can quickly realize the image text style transfer. The following figure is some results of the data synthesis tool.
littletomatodonkey's avatar
littletomatodonkey 已提交
33 34

<div align="center">
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
35
    <img src="doc/images/10.png" width="1000">
littletomatodonkey's avatar
littletomatodonkey 已提交
36 37 38 39
</div>


<a name="Preparation"></a>
W
weishengyu 已提交
40 41
#### Preparation

W
weishengyu 已提交
42
1. Please refer the [QUICK INSTALLATION](../doc/doc_en/installation_en.md) to install PaddlePaddle. Python3 environment is strongly recommended.
W
weishengyu 已提交
43 44 45
2. Download the pretrained models and unzip:

```bash
littletomatodonkey's avatar
littletomatodonkey 已提交
46 47
cd StyleText
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/style_text/style_text_models.zip
W
weishengyu 已提交
48 49 50
unzip style_text_models.zip
```

littletomatodonkey's avatar
littletomatodonkey 已提交
51
If you save the model in another location, please modify the address of the model file in `configs/config.yml`, and you need to modify these three configurations at the same time:
W
weishengyu 已提交
52 53 54 55 56 57 58 59 60 61 62 63

```
bg_generator:
  pretrain: style_text_rec/bg_generator
...
text_generator:
  pretrain: style_text_models/text_generator
...
fusion_generator:
  pretrain: style_text_models/fusion_generator
```

littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
64 65
<a name="Quick_Start"></a>
### Quick Start
W
weishengyu 已提交
66

littletomatodonkey's avatar
littletomatodonkey 已提交
67
#### Synthesis single image
W
weishengyu 已提交
68

littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
69
1. You can run `tools/synth_image` and generate the demo image, which is saved in the current folder.
W
weishengyu 已提交
70

littletomatodonkey's avatar
littletomatodonkey 已提交
71
```python
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
72
python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
W
weishengyu 已提交
73 74
```

75 76 77 78
* Note 1: The language options is correspond to the corpus. Currently, the tool only supports English, Simplified Chinese and Korean.
* Note 2: Synth-Text is mainly used to generate images for OCR recognition models. 
  So the height of style images should be around 32 pixels. Images in other sizes may behave poorly.

littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99

For example, enter the following image and corpus `PaddleOCR`.

<div align="center">
    <img src="examples/style_images/2.jpg" width="300">
</div>

The result `fake_fusion.jpg` will be generated.

<div align="center">
    <img src="doc/images/4.jpg" width="300">
</div>

What's more, the medium result `fake_bg.jpg` will also be saved, which is the background output.

<div align="center">
    <img src="doc/images/7.jpg" width="300">
</div>


`fake_text.jpg` * `fake_text.jpg` is the generated image with the same font style as `Style Input`.
W
weishengyu 已提交
100 101


littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
102 103 104
<div align="center">
    <img src="doc/images/8.jpg" width="300">
</div>
W
weishengyu 已提交
105 106


littletomatodonkey's avatar
littletomatodonkey 已提交
107
#### Batch synthesis
W
weishengyu 已提交
108

littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
109
In actual application scenarios, it is often necessary to synthesize pictures in batches and add them to the training set. StyleText can use a batch of style pictures and corpus to synthesize data in batches. The synthesis process is as follows:
W
weishengyu 已提交
110 111

1. The referenced dataset can be specifed in `configs/dataset_config.yml`:
littletomatodonkey's avatar
littletomatodonkey 已提交
112

littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
113 114 115 116 117 118 119 120 121
   * `Global`
     * `output_dir:`:Output synthesis data path.
   * `StyleSampler`
     * `image_home`:style images' folder.
     * `label_file`:Style images' file list. If label is provided, then it is the label file path.
     * `with_label`:Whether the `label_file` is label file list.
   * `CorpusGenerator`
     * `method`:Method of CorpusGenerator,supports `FileCorpus` and `EnNumCorpus`. If `EnNumCorpus` is used,No other configuration is needed,otherwise you need to set `corpus_file` and `language`.
     * `language`:Language of the corpus.
W
Wei Shengyu 已提交
122
     * `corpus_file`: Filepath of the corpus. Corpus file should be a text file which will be split by line-endings('\n'). Corpus generator samples one line each time.
W
Wei Shengyu 已提交
123 124 125


Example of corpus file: 
W
Wei Shengyu 已提交
126 127 128
```
PaddleOCR
飞桨文字识别
W
Wei Shengyu 已提交
129 130
StyleText
风格文本图像数据合成
W
Wei Shengyu 已提交
131
```
W
weishengyu 已提交
132

littletomatodonkey's avatar
littletomatodonkey 已提交
133
We provide a general dataset containing Chinese, English and Korean (50,000 images in all) for your trial ([download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/style_text/chkoen_5w.tar)), some examples are given below :
littletomatodonkey's avatar
littletomatodonkey 已提交
134 135 136 137 138

<div align="center">
     <img src="doc/images/5.png" width="800">
</div>

W
weishengyu 已提交
139 140 141 142 143
2. You can run the following command to start synthesis task:

   ``` bash
   python -m tools.synth_dataset.py -c configs/dataset_config.yml
   ```
144 145 146 147 148 149 150 151 152 153 154 155
We also provide example corpus and images in `examples` folder. 
    <div align="center">
        <img src="examples/style_images/1.jpg" width="300">
        <img src="examples/style_images/2.jpg" width="300">
    </div>
If you run the code above directly, you will get example output data in `output_data` folder.
You will get synthesis images and labels as below:
   <div align="center">
       <img src="doc/images/12.png" width="800">
   </div>
There will be some cache under the `label` folder. If the program exit unexpectedly, you can find cached labels there.
When the program finish normally, you will find all the labels in `label.txt` which give the final results.
littletomatodonkey's avatar
littletomatodonkey 已提交
156

littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
157 158
<a name="Applications"></a>
### Applications
littletomatodonkey's avatar
littletomatodonkey 已提交
159 160 161
We take two scenes as examples, which are metal surface English number recognition and general Korean recognition, to illustrate practical cases of using StyleText to synthesize data to improve text recognition. The following figure shows some examples of real scene images and composite images:

<div align="center">
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
162
    <img src="doc/images/11.png" width="800">
littletomatodonkey's avatar
littletomatodonkey 已提交
163 164 165 166 167
</div>


After adding the above synthetic data for training, the accuracy of the recognition model is improved, which is shown in the following table:

L
littletomatodonkey 已提交
168

littletomatodonkey's avatar
littletomatodonkey 已提交
169
| Scenario | Characters | Raw Data | Test Data | Only Use Raw Data</br>Recognition Accuracy | New Synthetic Data | Simultaneous Use of Synthetic Data</br>Recognition Accuracy | Index Improvement |
L
littletomatodonkey 已提交
170 171 172
| -------- | ---------- | -------- | -------- | -------------------------- | ------------ | ---------------------- | -------- |
| Metal surface | English and numbers | 2203     | 650      | 0.5938                     | 20000        | 0.7546                 | 16%      |
| Random background | Korean       | 5631     | 1230     | 0.3012                     | 100000       | 0.5057                 | 20%      |
littletomatodonkey's avatar
littletomatodonkey 已提交
173 174 175 176


<a name="Code_structure"></a>
### Code Structure
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
177

littletomatodonkey's avatar
littletomatodonkey 已提交
178
```
littletomatodonkey's avatar
littletomatodonkey 已提交
179
StyleText
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
180
|-- arch                        // Network module files.
littletomatodonkey's avatar
littletomatodonkey 已提交
181 182 183 184 185
|   |-- base_module.py
|   |-- decoder.py
|   |-- encoder.py
|   |-- spectral_norm.py
|   `-- style_text_rec.py
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
186
|-- configs                     // Config files.
littletomatodonkey's avatar
littletomatodonkey 已提交
187 188
|   |-- config.yml
|   `-- dataset_config.yml
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
189 190 191 192 193 194 195 196
|-- engine                      // Synthesis engines.
|   |-- corpus_generators.py    // Sample corpus from file or generate random corpus.
|   |-- predictors.py           // Predict using network.
|   |-- style_samplers.py       // Sample style images.
|   |-- synthesisers.py         // Manage other engines to synthesis images.
|   |-- text_drawers.py         // Generate standard input text images.
|   `-- writers.py              // Write synthesis images and labels into files.
|-- examples                    // Example files.
littletomatodonkey's avatar
littletomatodonkey 已提交
197 198 199 200 201 202
|   |-- corpus
|   |   `-- example.txt
|   |-- image_list.txt
|   `-- style_images
|       |-- 1.jpg
|       `-- 2.jpg
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
203
|-- fonts                       // Font files.
littletomatodonkey's avatar
littletomatodonkey 已提交
204 205 206
|   |-- ch_standard.ttf
|   |-- en_standard.ttf
|   `-- ko_standard.ttf
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
207
|-- tools                       // Program entrance.
littletomatodonkey's avatar
littletomatodonkey 已提交
208
|   |-- __init__.py
littletomatodonkey's avatar
fix doc  
littletomatodonkey 已提交
209 210 211
|   |-- synth_dataset.py        // Synthesis dataset.
|   `-- synth_image.py          // Synthesis image.
`-- utils                       // Module of basic functions.
littletomatodonkey's avatar
littletomatodonkey 已提交
212 213 214 215 216 217
    |-- config.py
    |-- load_params.py
    |-- logging.py
    |-- math_functions.py
    `-- sys_funcs.py
```