This release introduces machine learning inference for the detection of the ColorChecker Classic 24.

Features

colour_checker_detection.detection

Machine Learning Inference

• Add colour_checker_detection.detection.detect_colour_checkers_inference definition. (#75, @KelSolaar)

The model used for inference is published on HuggingFace, and was trained on a purposely constructed dataset.

The model has only been trained on ColorChecker Classic 24 images and will not work with ColorChecker Nano or ColorChecker SG images.

Inference is performed by a script licensed under the terms of the GNU Affero General Public License v3.0 as it uses the Ultralytics YOLOv8 API which is incompatible with the BSD-3-Clause.

Fixes

• Fix incorrect colour checker flipping detection in colour_checker_detection.detection.detect_colour_checkers_segmentation definition. (#73, @andieich, @mexicantexan, @KelSolaar)

Changes

• The colour_checker_detection.detection.detect_colour_checkers_segmentation definition has been overhauled to provide a consistent interface with the colour_checker_detection.detection.detect_colour_checkers_inference definition. It also features some improvements following discussions with contributors. (#53, #73, #74, @andieich, @mexicantexan, @TimWalter, @KelSolaar)

Object	Signature	Author
colour_checker_detection.detection.detect_colour_checkers_segmentation	detect_colour_checkers_segmentation( image: str | ArrayLike, samples: int = 32, cctf_decoding: Callable = eotf_sRGB, apply_cctf_decoding: bool = False, segmenter: Callable = segmenter_default, segmenter_kwargs: dict | None = None, show: bool = False, additional_data: bool = False, **kwargs: Any) -> Tuple[DataDetectionColourChecker | NDArrayFloat, ...]	@KelSolaar

Object	Name	Author
colour_checker_detection.colour_checkers_coordinates_segmentation	segmenter_default	@KelSolaar

• colour_checker_detection.extract_colour_checkers_segmentation: (@KelSolaar)
  • Remove

This release is a compatibility release with Colour 0.4.4.

The following scientific packages minimum versions are required:

• colour-science >= 0.4.4

This release is a compatibility release with Colour 0.4.3.

The following scientific packages minimum versions are required:

• numpy >= 1.22
• scipy >= 1.8
• colour-science >= 0.4.3

This release is a compatibility release with Colour 0.4.2 providing support for Python 3.11.

The minimum Python version is 3.9 and the following scientific packages minimum versions are required:

• numpy >= 1.20
• scipy >= 1.7
• colour-science >= 0.4.2

This release is a compatibility release with Colour 0.4.1.

Support for Python 2.7 has been dropped!

It is now possible to detect the ColorChecker SG in an image.

Changes

• The signatures and return values of various definitions have been updated. (@KelSolaar)

Please refer to the following attributes and definitions:

• colour_checker_detection.SETTINGS_SEGMENTATION_COLORCHECKER_CLASSIC
• colour_checker_detection.SETTINGS_SEGMENTATION_COLORCHECKER_SG
• colour_checker_detection.colour_checkers_coordinates_segmentation
• colour_checker_detection.extract_colour_checkers_segmentation
• colour_checker_detection.detect_colour_checkers_segmentation

This release is a compatibility release with Colour 0.3.16.

This is the last feature release to support Python 2.7!

Initial release for Colour - Checker Detection. (@kelsolaar)