The deepdeblur from fcat97

deepdeblur's Introduction

DeepDeblur: Text Image Recovery from Blur to Sharp

This work focuses on recovering the blurry text image.

Introduction

Based on the deep neural network, a new short connection scheme is used. Trained by the pixel regression, higher visual quality of the image can be recovered by the network from the blurry one.

Sequential Highway Connection (SHC) structure
Loss curve comparing with the ResNet Structure:
Visualization

Citation

If you find our work useful in your research and relevant works, please consider citing:

@Article{Mei2019,
author="Mei, Jianhan and Wu, Ziming and Chen, Xiang and Qiao, Yu and Ding, Henghui and Jiang, Xudong",
title="DeepDeblur: text image recovery from blur to sharp",
journal="Multimedia Tools and Applications",
year="2019",
issn="1573-7721",
doi="10.1007/s11042-019-7251-y",
url="https://doi.org/10.1007/s11042-019-7251-y"
}

Required Environment

Ubuntu 16.04
Python 2/3, in case you need the sufficient scientific computing packages, we recommend you to install anaconda.
Tensorflow >= 1.5.0
Keras >= 2.2.0
Optional: if you need GPUs acceleration, please install CUDA that the version requires >= 9.0

Running The Demo

Text Image Dataset Generation

Check the matlab script 'Matlab/RunProcess.m': The path of the text images should contain raw sharp text images. You can build your own dataset by convert PDF files into raw image files and save them to the text image path in "Matlab/RunProcess.m".

Then run the matlab script 'Matlab/RunProcess.m', which helps to build the training dataset.
Training

Check the training data and model saving paths in "train.py", for which the training data should be consistent with the previous step. Then run the following script:
```
python train.py
```
Testing

Check the testing model and data paths in "test.py". Then run the following script:
```
python test.py
```