https://github.com/muhammedbuyukkinaci/detext

A computer vision project (image segmentation project) which aims to remove texts on images using Unet model. Tensorflow 2 is used as a ML library.
https://github.com/muhammedbuyukkinaci/detext

image-segmenation-unet image-segmentation image-segmentation-practice image-segmentation-tensorflow keras-segmentation keras-unet remove-text-on-images tensorflow tensorflow-2 tensorflow-image-segmentation tensorflow-keras-unet tensorflow-segmentation tensorflow2-image-segmentation tensorflow2-unet text-removal-using-unet unet unet-image-segmentation unet-segmentation unet-tensorflow

Last synced: about 2 months ago
JSON representation

A computer vision project (image segmentation project) which aims to remove texts on images using Unet model. Tensorflow 2 is used as a ML library.

• Host: GitHub
• URL: https://github.com/muhammedbuyukkinaci/detext
• Owner: MuhammedBuyukkinaci
• Created: 2020-03-22T16:09:12.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2023-03-24T23:02:39.000Z (almost 2 years ago)
• Last Synced: 2024-11-02T09:42:04.773Z (2 months ago)
• Topics: image-segmenation-unet, image-segmentation, image-segmentation-practice, image-segmentation-tensorflow, keras-segmentation, keras-unet, remove-text-on-images, tensorflow, tensorflow-2, tensorflow-image-segmentation, tensorflow-keras-unet, tensorflow-segmentation, tensorflow2-image-segmentation, tensorflow2-unet, text-removal-using-unet, unet, unet-image-segmentation, unet-segmentation, unet-tensorflow
• Language: Python
• Homepage: https://muhammedbuyukkinaci.com
• Size: 32.4 MB
• Stars: 14
• Watchers: 2
• Forks: 3
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# DeText

A computer vision project which aims to remove text on images

It is a ready-to-run code after downloading data from [here](https://www.kaggle.com/jessicali9530/celeba-dataset) .

# Dependencies

```pip3 install -r requirements.txt```

# Training

Open up a terminal in the main directory and run one of below commands.

If you want to train from scratch:

```bash run_from_scratch.sh ```

If you don't want to train from scratch:

```bash run_from_pretrained.sh ```

# Notebook

Notebooks are in notebooks folder.

# Data

[CelebFaces Attributes (CelebA) Dataset](https://www.kaggle.com/jessicali9530/celeba-dataset) is used in the project.

This is a repository containing more than 200,000 images of various celebrities.

Download the dataset and put the downloaded zip file in main directory. Then, unzip it.

The directories and files should be listed as below:

![alt text](tree.png)

# Architecture

UNet is used as architecture. I customized it a little. About 2 million Parameters.

![alt text](https://miro.medium.com/max/5998/1*eKrh8FqJL3jodebYlielNg.png) 

# Predictions

Predictions for some testing images are below.

![alt text](results.png)