Skip to main content
Archived

This project has been archived by its maintainers, and is no longer receiving any updates.

face-symmetrizer

PyPI version GitHub release

pre-commit.ci status

  • Easy symmetrizer for an image contained face(s)

Install

pip install face-symmetrizer

How

  • Here is an example image of two people

fig0

Command

$ fsym -h
usage: fsym [-h] [-s] [-S] [-q] [-o dir] file [file ...]

Easy symmetrizer for an image contained face(s)

positional arguments:
  file                  input image files

optional arguments:
  -h, --help            show this help message and exit
  -s, --show            show images (default: False)
  -S, --save            save images (default: False)
  -q, --quiet           make log quiet (default: False)
  -o dir, --outdir dir  directory when saving images (default: .)
  • Detect with window and save symmetrized images to outimg
$ fsym img/two_people.jpg -o outimg -s --save
[+]image: img/two_people.jpg
[+]2 face(s) was detected.
[+]face: 0 # open window when using `-s`
[+]save: outimg/two_people.face-0.left_cropped.jpg
[+]save: outimg/two_people.face-0.left_cropped_inner.jpg
[+]save: outimg/two_people.face-0.left_cropped_outer.jpg
[+]save: outimg/two_people.face-0.right_cropped.jpg
[+]save: outimg/two_people.face-0.right_cropped_inner.jpg
[+]save: outimg/two_people.face-0.right_cropped_outer.jpg
[+]face: 1 # open window when using `-s`
[+]save: outimg/two_people.face-1.left_cropped.jpg
[+]save: outimg/two_people.face-1.left_cropped_inner.jpg
[+]save: outimg/two_people.face-1.left_cropped_outer.jpg
[+]save: outimg/two_people.face-1.right_cropped.jpg
[+]save: outimg/two_people.face-1.right_cropped_inner.jpg
[+]save: outimg/two_people.face-1.right_cropped_outer.jpg

Library

  • First, load an image
from face_symmetrizer import FaceSym

# load from local file path
f = FaceSym("img/two_people.jpg")
# or, load from URL
# f = FaceSym("https://raw.githubusercontent.com/ageitgey/"
#             "face_recognition/master/examples/two_people.jpg")


# ATTRS: ['image_location',
#         'f_img', 'f_img_PIL', 'image_size',
#         'face_locations', 'face_landmarks',
#         'mid_face_locations', 'face_count']
  • Get & show a full image
f.get_full_image(show=True) #=> <PIL.Image.Image>

fig1

  • Get & show an image of a rectangle drawn around a face.
f.get_face_box_drawed_image(show=True) #=> <PIL.Image.Image>

fig2

  • Get & show cropped face(s)
f.get_cropped_face_images(show=True) #=> [<PIL.Image.Image>, ...]

fig3 fig4

  • Get & show symmetrized images (face: 0)
f.get_symmetrized_images(show=True, idx=0)
#=> (left_cropped, left_cropped_inner, left_cropped_outer,
#    right_cropped, right_cropped_inner, right_cropped_outer)

fig5

  • Get & show symmetrized images (face: 1)
f.get_symmetrized_images(show=True, idx=1)

fig6

LICENSE

MIT

Metadata

Release files for face-symmetrizer 1.8.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for face-symmetrizer 1.8.1
File Size Uploaded
face_symmetrizer-1.8.1.tar.gz 7.3 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for face-symmetrizer 1.8.1
File Interpreter ABI Platform
face_symmetrizer-1.8.1-py3-none-any.whl Python 3 none any Details

Total release size: 15.4 kB

Release files / face_symmetrizer-1.8.1.tar.gz

Download URL face_symmetrizer-1.8.1.tar.gz
Size 7.3 kB
Tags Source
SHA-256 checksum
How to use checksums
0f4b831b0f584d8329049cbc8885dcd1b38cab7a7c3ff990bbdc6eff7e397f6e
BLAKE2b-256 checksum
How to use checksums
95a96b310be341b2922b3c0bff03b799ea21e0a2a3841b5ca83e5d0d9a18300a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.1 CPython/3.9.13

Release files / face_symmetrizer-1.8.1-py3-none-any.whl

Download URL face_symmetrizer-1.8.1-py3-none-any.whl
Size 8.1 kB
Tags Python 3
SHA-256 checksum
How to use checksums
fd4bcadf237bedb582815826b7ea23fbce7e0f4b41377ade7cea5f42de1e71e5
BLAKE2b-256 checksum
How to use checksums
a4ab79db3e7ee8a98b5f8d9b9c33406ad5f3c93fea58b937b6d476d4fed16cd6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.1 CPython/3.9.13
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page