Pixel Classification using ilastik


This workflow classifies, or segments, the pixels of an image given user annotations. It is especially suited if the objects of interests are visually (brightness, color, texture) distinct from their surrounding. Users can iteratively select pixel features and provide pixel annotations through a live visualization of selected feature values and current prediction responses. Upon users' satisfaction, the workflow then predicts the remaining unprocessed image(s) regions or new images (as batch processing). Users can export (as images of various formats): selected features, annotations, predicted classification probability, simple segmentation, etc. This workflow is often served as one of the first step options for other workflows offered by ilastik, such as object classification, automatic tracking.



This library gives the numpy-based infrastructure functions for image processing with a focus on bioimage informatics. It provides image filtering and morphological processing as well as feature computation (both image-level features such as Haralick texture features and SURF local features). These can be used with other Python-based libraries for machine learning to build a complete analysis pipeline.

Mahotas is appropriate for users comfortable with programming or builders of end-user tools.

==== Strengths

The major strengths are in speed and quality of documentation. Almost all of the functionality is implemented in for multiple dimensions. It can be used with other Python packages which provide additional functionality.

Mahotas and all packages on which it relies are open-source.