apoc 0.5.0

Accelerated Pixel and Object Classifiers based on OpenCL

Accelerated Pixel and Object Classifiers (APOC)

clEsperanto meets sklearn

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 = features = apoc.PredefinedFeatureSet.medium_quick.value

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

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")

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

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

imshow(classification_result)

More detailed examples

• Object segmentation
• Object classification
• Pixel classifier (including benchmarking).
• Continue training of pixel classifiers using multiple training image pairs
• Generating custom feature stacks

Installation

You can install apoc via [pip]. Note: you also need pyopencl.

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.