Skip to main content

Python module to segment the visible circular area of endoscopic images.

Project description

Description

Endoseg is a Python package that facilitates the segmentation of the visible circular area of endoscopic images.

Install dependencies

  • Numpy
# Ubuntu/Debian
$ sudo apt update
$ sudo apt install python3-pip
$ python3 -m pip install numpy --user
  • OpenCV
# Ubuntu/Debian
$ sudo apt update
$ sudo apt install libopencv-dev python3-opencv

Install with pip

$ python3 -m pip install endoseg --user

Install from source

$ git clone https://github.com/luiscarlosgph/endoseg.git
$ cd endoseg
$ python3 setup.py install --user

Run

$ git clone https://github.com/luiscarlosgph/endoseg.git
$ cd endoseg
$ python3 -m endoseg.run --input data/demo.jpg --output-seg data/demo_seg.png --output-crop data/demo_crop.jpg
Input image Output segmentation Output crop

Note that the output crop is a square cut of the area within the segmentation mask.

Exemplary code snippet

# Read input image
im = cv2.imread('input_image.jpg', cv2.IMREAD_UNCHANGED)

# Segment the visible area of the endoscopic image
segmenter = endoseg.Segmenter()
seg = segmenter.segment(im)

# Save the segmentation to file
cv2.imwrite('output_segmentation.png', seg)

# Get a rectangular crop of the visible area
crop = segmenter.get_rect_crop(im)

# Save the crop to file
cv2.imwrite('output_crop.jpg', crop)

License

This code is released under an MIT license.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

endoseg-0.6.0.tar.gz (6.4 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page