SLDC is a framework created for accelerating development of large image analysis workflows. It is especially well suited for solving more or less complex problems of object detection and classification in multi-gigapixel images.
The framework encapsulates problem-independent logic such as parallelism, memory constraints (due to large image handling) while providing a concise way of declaring problem-dependent components of the implementer's workflows.
The algorithm used by the framework as well as some toy examples are presented in the Wiki.
The framework currently works under Python 2.7 and 3.5.
The required dependencies are the following :
- Numpy (>= 1.10, might work with earlier versions)
- OpenCV (>= 3.0)
- Pillow (>= 3.1.1)
- joblib (>= 0.9.4)
- Shapely (>= 1.5.13)
- Scipy (>= 0.18.1)
Simply: pip install sldc
On Windows, some .dll are needed by shapely and are not installed by pip when you install sldc. Therefore, you might have to install
shapely yourself from conda (i.e. conda install shapely) or from here after having run pip install sldc.
The library is image format agnostic and therefore allows you to integrate it with any existing image format by implementing some interfaces. However, some bindings were implemented for integrating SLDC with:
If you use SLDC in a scientific publication, we would appreciate citations: Mormont & al., Benelearn, 2016.
The framework was initially developed in the context of this master thesis.