Image-based object detection and feature extraction from a reconstructed charged particle image of a volume of interest

摘要

Techniques, systems, and devices are disclosed for analyzing a reconstructed charged particle image of a volume of interest from charged particle detector measurements to detect objects within the volume of interest and then extracting features from the detected objects based on their statistical and geometric properties. In one aspect, this technique partitions the reconstructed charged particle image of the volume into a set of voxels, wherein each voxel is associated with an intensity value. The technique next performs a segmentation operation on the said image to identify a subset of the set of voxels as object-candidate voxels for generating objects. The technique then performs a connected-component analysis on the object-candidate voxels to identify one or more objects within the said image of the volume. The technique subsequently extracts a set of object features from each identified object based at least on the statistical and geometric properties of the identified object.