Skip to content

An attempt to generate latent siblings faces by Machine Learning

License

Notifications You must be signed in to change notification settings

shin-sforzando/latent-siblings

Repository files navigation

latent-siblings

An attempt to generate latent siblings faces by Machine Learning.

How to

Setup

ImageMagick

brew install imagemagick

Python Libraries

pip install -r requirements.txt

Prepare datasets

TSKinFace

Tri-subject Kinship Face Database.

Copyright 2015, Xiaoyang Tan The dataset is provided for research purposes to a researcher only and not for any commercial use. Please do not release the data or redistribute this link to anyone else without our permission. Contact {x.tan}@nuaa.edu.cn if any question.

If you use this dataset, please cite it as,

Xiaoqian Qin, Xiaoyang Tan,Songcan Chen, Tri-Subject Kinship Verification: Understanding the Core of A Family. IEEE Transactions on Multimedia, 2015

Download

Download here.

Preprocess and Combine

Make the mirror image from Son's and Daughter's before combining.

python tskinface_preprocessor.py

These preprocessed images are stored in data/TSKinFace/preprocessed. These combined images are stored in data/TSKinFace/combined.

Crop Faces from Image File

python face_extractor.py FACE_IMG_PATH

Cropped files will export at FACE_IMG_PATH directory.

You can change the resolution to export with -r option. You can change the method of resize with -i option.

Misc.

This program is brought by Shin'ichiro SUZUKI to KUAD Design Project II A 2019.

About

An attempt to generate latent siblings faces by Machine Learning

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages