Skip to content
EVAnalyzer Docs

Extract ROIs

The Extract ROIs command reads the labelled image produced by Connected Components (or Watershed) and creates one segmentation-class object per labelled region. These objects are the raw candidates passed to Classify ROIs for final filtering and class assignment.

This is the boundary between “pixels” and “objects” in the pipeline: everything before this step operates on whole images, and everything after operates on individually addressable regions with their own metrics, mask, and object ID.

Each labelled region turns into an addressable object record with its own mask, geometry, and metrics

Parameters

Section titled “Parameters”
ParameterDescription
Max objects before failHard upper limit on the number of regions extracted. If more regions are found the pipeline step fails, preventing runaway processing on misconfigured segmentation (default: –1 = unlimited)

Pipeline position

Section titled “Pipeline position”
Threshold → Connected Components → [Watershed] → Extract ROIs → Classify ROIs

Extract ROIs is always followed by Classify ROIs. The segmentation class assigned here is the intermediate class used internally; the final named object class is assigned by Classify ROIs.