hefv57/apoc

Accelerated Pixel and Object Classifiers (APOC)

clesperanto meets scikit-learn to classify pixels and objects in images, on a GPU using OpenCL. This repository contains the backend for python developers. User-friendly plugins for Fiji and napari can be found here:

• napari-accelerated-pixel-and-object-classification
• clijx-accelerated-pixel-and-object-classification

For training classifiers from pairs of image and label-mask folders, please see this notebook.

Object segmentation

With a given blobs image and a corresponding annotation...

from skimage.io import imread, imshow
import pyclesperanto_prototype as cle
import numpy as np
import apoc

image = imread('blobs.tif')
imshow(image)

manual_annotations = imread('annotations.tif')
imshow(manual_annotations, vmin=0, vmax=3)

... objects can be segmented (see full example):

# define features: original image, a blurred version and an edge image
features = apoc.PredefinedFeatureSet.medium_quick.value

# Training
clf = apoc.ObjectSegmenter(opencl_filename='object_segmenter.cl', positive_class_identifier=2)
clf.train(features, manual_annotations, image)

# Prediction
segmentation_result = clf.predict(image=image)
cle.imshow(segmentation_result, labels=True)

Object classification

With a given annotation, blobs can also be classified according to their shape (see full example).

features = 'area,mean_max_distance_to_centroid_ratio,standard_deviation_intensity'

# Create an object classifier
classifier = apoc.ObjectClassifier("object_classifier.cl")

# Training
classifier.train(features, segmentation_result, annotation, image)

# Prediction / determine object classification
classification_result = classifier.predict(segmentation_result, image)

imshow(classification_result)

More detailed examples

• Object segmentation
• Object classification
• Object classification based on custom measurement tables
• Pixel classifier (including benchmarking).
• Output probability maps
• Continue training of pixel classifiers using multiple training image pairs
• Generating custom feature stacks

Installation

You can install apoc using pip. Note: you need to install pyopencl in advance using conda:

conda install pyopencl
pip install apoc

Contributing

Contributions are very welcome. Tests can be run with pytest, please ensure the coverage at least stays the same before you submit a pull request.

License

Distributed under the terms of the BSD-3 license, "apoc" is free and open source software

Issues

If you encounter any problems, please open a thread on image.sc along with a detailed description and tag @haesleinhuepf.