A basic library to crop largest face from the images.
Mukham (ముఖం; mook-hum) means face in Telugu! mukham is a simple library to detect the largest face in a given image.
The face detection is performed using the DNN algorithm provided by
opencv-python. The largest face is the box with largest enclosing area from the bounds of candidate faces detected.
This package was written and tested in python 3.7+. This package requires the following dependencies:
The package can be installed as follows:
pip install mukham
The package can be used through one of the following ways.
python -m mukham -i/--input path/to/input_image -o/--ouput path/to/output_largest_face -c/--conf confidence_threshold
This will print the top left and bottom right corner of the bounding box for the largest face. The
(i)nput argument is required. The
(o)utput path is optional, if given will save the largest face image to this path. The
(c)onf is optional, otherwise must be a floating point number between 0 and 1 with default value of
from mukham.detector import detect_largest_face bounding_box = detect_largest_face(path_to_input_img, out_path=path_to_output_img, min_conf=confidence_threshold)
in_path is a required argument for path to the input image. The
out_path is an optional keyword argument default to
None, if given will save the largest face image to this path.
min_conf is also a keyword argument with default set to
detect_largest_face will return a 2x2 array of the top left and bottom right corner of the bounding box for the largest face.
Unit tests have also been written which can be run as follows:
python -m unittest mukham.tests.test
Release history Release notifications | RSS feed
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size mukham-1.0.9-py3-none-any.whl (10.3 MB)||File type Wheel||Python version py3||Upload date||Hashes View|
|Filename, size mukham-1.0.9.tar.gz (10.3 MB)||File type Source||Python version None||Upload date||Hashes View|