Face Morpher

Built with Python, dlib, Numpy, Scipy, dlib.

Requirements

• pip install -r requirements.txt
• Download http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2 and extract file.
• Export environment variable DLIB_DATA_DIR to the folder where shape_predictor_68_face_landmarks.dat is located. Default data. E.g export DLIB_DATA_DIR=/Downloads/data

Either:

• Use as local command-line utility
• Use as pip library
• Try out in a docker container

Use as local command-line utility

$ git clone https://github.com/alyssaq/face_morpher

Morphing Faces

Morph from a source to destination image:

python facemorpher/morpher.py --src=<src_imgpath> --dest=<dest_imgpath> --plot

Morph through a series of images in a folder:

python facemorpher/morpher.py --images=<folder> --out_video=out.avi

All options listed in morpher.py (pasted below):

Morph from source to destination face or
Morph through all images in a folder

Usage:
    morpher.py (--src=<src_path> --dest=<dest_path> | --images=<folder>)
            [--width=<width>] [--height=<height>]
            [--num=<num_frames>] [--fps=<frames_per_second>]
            [--out_frames=<folder>] [--out_video=<filename>]
            [--plot] [--background=(black|transparent|average)]

Options:
    -h, --help              Show this screen.
    --src=<src_imgpath>     Filepath to source image (.jpg, .jpeg, .png)
    --dest=<dest_imgpath>   Filepath to destination image (.jpg, .jpeg, .png)
    --images=<folder>       Folderpath to images
    --width=<width>         Custom width of the images/video [default: 500]
    --height=<height>       Custom height of the images/video [default: 600]
    --num=<num_frames>      Number of morph frames [default: 20]
    --fps=<fps>             Number frames per second for the video [default: 10]
    --out_frames=<folder>   Folder path to save all image frames
    --out_video=<filename>  Filename to save a video
    --plot                  Flag to plot images to result.png [default: False]
    --background=<bg>       Background of images to be one of (black|transparent|average) [default: black]
    --version               Show version.

Averaging Faces

Average faces from all images in a folder:

python facemorpher/averager.py --images=<images_folder> --out=average.png

All options listed in averager.py (pasted below):

Face averager

Usage:
    averager.py --images=<images_folder> [--blur] [--plot]
            [--background=(black|transparent|average)]
            [--width=<width>] [--height=<height>]
            [--out=<filename>] [--destimg=<filename>]

Options:
    -h, --help             Show this screen.
    --images=<folder>      Folder to images (.jpg, .jpeg, .png)
    --blur                 Flag to blur edges of image [default: False]
    --width=<width>        Custom width of the images/video [default: 500]
    --height=<height>      Custom height of the images/video [default: 600]
    --out=<filename>       Filename to save the average face [default: result.png]
    --destimg=<filename>   Destination face image to overlay average face
    --plot                 Flag to display the average face [default: False]
    --background=<bg>      Background of image to be one of (black|transparent|average) [default: black]
    --version              Show version.

Steps (facemorpher folder)

1. Locator

• Locates face points
• For a different locator, return an array of (x, y) control face points

2. Aligner

• Align faces by resizing, centering and cropping to given size

3. Warper

• Given 2 images and its face points, warp one image to the other
• Triangulates face points
• Affine transforms each triangle with bilinear interpolation

4a. Morpher

• Morph between 2 or more images

4b. Averager

• Average faces from 2 or more images

Blender

Optional blending of warped image:

• Weighted average
• Alpha feathering
• Poisson blend

Examples - Being John Malkovich

Create a morphing video between the 2 images:

(out.avi played and recorded as gif)

Save the frames to a folder:

Plot the frames:

Average all face images in a folder:

85 images used

Use as pip library

$ pip install facemorpher

Examples

Additional options are exactly the same as the command line

import facemorpher

# Get a list of image paths in a folder
imgpaths = facemorpher.list_imgpaths('imagefolder')

# To morph, supply an array of face images:
facemorpher.morpher(imgpaths, plot=True)

# To average, supply an array of face images:
facemorpher.averager(['image1.png', 'image2.png'], plot=True)

Once pip installed, 2 binaries are also available as a command line utility:

$ facemorpher --src=<src_imgpath> --dest=<dest_imgpath> --plot
$ faceaverager --images=<images_folder> --plot

Try out in a docker container

Mount local folder to /images in docker container, run it and enter a bash session. --rm removes the container when you close it.

$ docker run -v  /Users/alyssa/Desktop/images:/images --name py3 --rm -it jjanzic/docker-python3-opencv bash

Once you're in the container, install facemorpher and try the examples listed above

root@0dad0912ebbe:/# pip install facemorpher
root@0dad0912ebbe:/# facemorpher --src=<img1> --dest=<img2> --plot

Documentation

http://alyssaq.github.io/face_morpher

Build & publish Docs

./scripts/publish_ghpages.sh

License

MIT