Computer Image Likeness Assessing Automation
CILISSA allows for the use of various metrics to perform full-reference image comparisons.
It features the most popular full-reference image quality metrics, image transformations and translations. CILISSA is also very extensible and new operations can be easily added.
CILISSA has an optional Qt-based graphical interface that lets you experiment with various operations, their orders and properties.
- Python >=3.9,<3.12
$ pip install cilissaBinaries for Windows and Linux can be found on GitHub releases.
Information about the GUI can be found in the cilissa_gui/README.md file.
Currently the CLI only supports working with a single pair of images.
The parameters of metrics and transformations can be modified by passing them to the --kwargs argument using the following format:
<operation-name>-<parameter-name>=<value>
where parameter-name uses hyphens (-) instead of underscores (_)
Documentation is hosted on Read the Docs.
CILISSA is under the terms of the MIT License, following all clarifications stated in the license file.