A package of image analysis algorithms suited for plants
Project description
LettuceSee
A package with high level functions for analyzing images of plants.
Example case
The following example showcases a miniature pipeline using lettuceSee and scikit-image functions.
An image of lettuce affected with necrosis is loaded in as a numpy array. After removing the alpha layer, applying the shw_segmentation function from the segment module removes the background of the image.
from lettuceSee import segment
import skimage
import matplotlib.pyplot as plt
image = skimage.io.imread(
r"C:\Users\chris\Documents\GitHub\tipburn_quantification\test_images"
r"\rgb\51-78-Lettuce_Correct_Tray_074-RGB-Original_pos2_LK120.png")
image = skimage.util.img_as_ubyte(skimage.color.rgba2rgb(image))
bg_mask = segment.shw_segmentation(image)
The initial segmentation looks decent, however there is still some background noise, as well as other plants intruding from the side. The function canny_central_ob is used to remove objects not attached to the central object, as well as connected objects with very different coloration.
bg_mask = segment.canny_central_ob(image=image, mask=bg_mask, sigma=2.5)
After finishing the background segmentation, the function barb_hue is used to segment green from brown tissue through the method described in Barbedo, 2016.
necrosis_mask = segment.barb_hue(image=image, bg_mask=bg_mask, div=3)
Installation
The package can be installed from the pypi test distribution trough:
python -m pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple/ lettuceSee=0.0.12
Anaconda
There is no dedicated lettuceSee installation for anaconda, if you do want to install the package within anaconda the following method is recommended: First create a new environment following the anaconda documentation. Activate your fresh environment and install pip:
conda install pip
Following this run the usual command to install lettuceSee. Note that mixing conda and pip can lead to unexpected errors, as both are package managers. As such it is recommended to do further installations in this environment trough pip.
Recommended extras
For visualization of the images, matplotlib is recommended. LettuceSee handles images as numpy arrays, which can be directly visualized trough matplotlib.pyplot. Matplotlib is not included in the installation of lettuceSee, but can be installed trough:
pip install matplotlib
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file lettuceSee-0.0.3.tar.gz
.
File metadata
- Download URL: lettuceSee-0.0.3.tar.gz
- Upload date:
- Size: 7.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 595cbb66a390caf884cce09264596f16888d8c544b751434c048f43f2a7a2fd2 |
|
MD5 | fbe9c91beeed575b5f1dcfdbd1ae6eef |
|
BLAKE2b-256 | 4883adafed9d03cda9aed6d6c20139ba0874bee11ec6f0709848f190a430b038 |
File details
Details for the file lettuceSee-0.0.3-py3-none-any.whl
.
File metadata
- Download URL: lettuceSee-0.0.3-py3-none-any.whl
- Upload date:
- Size: 7.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.7
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5f585e932f078f7b6f37e0ed30541ff990cca78cb09f291dedcc94018f29272b |
|
MD5 | 2f5af7dff00e075b349189500a05b249 |
|
BLAKE2b-256 | c097013098372253ab164659e02f75ec8e780726e7730a4761c1379cdd3e6a2a |