2020-08-28 12:12:32 +00:00
# JMTrans - Japanese Manga Translator
2020-12-09 13:39:13 +00:00
get japanese manga from url to translate manga image using SickZil(text segmentation model), google ocr(or window ocr) and eztrans xp(or google translator)
gui version 0.3a is released. Window ocr and google translate api are now supported.
2020-12-08 12:58:33 +00:00
download latest version (using eztrans xp(or google translator), support multi lang)
2020-09-09 04:17:21 +00:00
https://github.com/ttop32/JMTrans/releases/latest/download/JMTrans.zip
2020-09-09 04:16:51 +00:00
2020-12-08 12:58:33 +00:00
pre released colab version (using google translator only, support multi lang)
2020-08-19 14:30:51 +00:00
https://colab.research.google.com/drive/1XbR7fNXtT4TGlLI1FBcCQv7Gj5mlDvwb?usp=sharing
2020-08-19 14:34:05 +00:00
2020-09-09 04:16:14 +00:00
2020-12-08 12:58:33 +00:00
2020-09-09 17:35:50 +00:00
# Result
2020-08-19 17:21:24 +00:00
2020-08-19 17:21:46 +00:00
2020-08-19 17:47:36 +00:00
2020-08-19 14:39:32 +00:00
2020-12-08 12:59:58 +00:00
# gui
2020-12-08 12:58:33 +00:00
# Required environment to run
- google ocr : google drive permission(credential file and scope file)
2020-12-11 05:57:54 +00:00
- window ocr : Microsoft.NET v4.0.30319,net core 3.1 runtime and window japanese ocr
2020-12-08 12:58:33 +00:00
- ez trans xp korea translator : ez trans xp program and ehnd
# How to use
2020-12-08 13:08:06 +00:00
- open the program and type manga site url then press enter
2020-12-08 12:58:33 +00:00
- It process translation (it takes time)
- it will create zip file on user's window download folder
2020-08-24 02:08:26 +00:00
2020-09-09 17:36:15 +00:00
# Supported URL
2020-08-24 02:08:26 +00:00
gallery-dl is used to download. Its support sites are:
2020-08-24 02:12:17 +00:00
- [supported site list ](https://github.com/mikf/gallery-dl/blob/master/docs/supportedsites.rst )
2020-08-24 02:08:26 +00:00
2020-12-08 12:58:33 +00:00
# Workflow
- use gallery-dl to get managa from inputted url
- do text segmentation from manga image using SickZil
- use opencv contour technique to detect text to crop text image based on text segmentation results
- get text from image using google ocr(or window ocr)
- convert japanese text to translated text using eztrans xp(or google translator)
- use pil to place translated text
# Run python
python gui.py
# pip install
pip install tensorflow-gpu==1.14.0
pip install requests
pip install PyQt5
pip install tqdm funcy opencv-python Pillow
2020-09-09 03:48:02 +00:00
pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib
2020-12-08 12:58:33 +00:00
pip install --upgrade pyinstaller==3.2.1
2020-09-09 03:48:02 +00:00
pip install cefpython3
pip install pywin32
pip install matplotlib
pip install imageio
2020-12-08 12:58:33 +00:00
pip install google_trans_new
pip install beautifulsoup4
pip install wget
pip install pyperclip
pip install astor==0.8.0
pip uninstall h5py
2020-12-08 13:03:19 +00:00
or
conda remove --name py35 --all
conda create --name py35 python=3.5
activate py35
pip install -r requirements.txt
pip freeze > requirements.txt
2020-12-08 12:58:33 +00:00
# Acknowledgement and References
- [gallery-dl ](https://github.com/mikf/gallery-dl )
- [SickZil-Machine ](https://github.com/KUR-creative/SickZil-Machine )
- [Tesseract ](https://github.com/tesseract-ocr/tesseract )
- [Pytesseract ](https://pypi.python.org/pypi/pytesseract )
- [nhocr ](https://github.com/fireae/nhocr )
- [OpenCV with Python wrapper ](https://pypi.org/project/opencv-python/ )
- [text-detection ](https://github.com/qzane/text-detection )
- [Google Translate API for Python ](https://pypi.org/project/googletrans/ )
- [google translate new ](https://github.com/lushan88a/google_trans_new )
- [ehnd ](https://github.com/sokcuri/ehnd )
2020-12-11 08:27:33 +00:00
- [ezTransWeb ](https://github.com/HelloKS/ezTransWeb )
2020-12-08 12:58:33 +00:00
- [google drive ](https://developers.google.com/drive/api/v3/quickstart/python )
- [flaticon ](https://www.flaticon.com/ )
- [cefpython ](https://github.com/cztomczak/cefpython )
2020-08-19 17:35:34 +00:00
