Martensitic Microstructures. Latest Clemex grain size development using machine learning capabilities. Requires Vision Lite, Core or Unlimited.

The Grain Size Application Package for Clemex Vision leverages machine learning capabilities, including a special instruction for martensitic grains. The new automatic algorithm provides a fast, reliable, and accurate way of optically identifying challenging martensitic microstructures.

Martensitic microstructures are difficult to analyze optically because of the materials’ resistance to etching techniques. Grain structures are barely visible and typically a lab will rely on the human eye to distinguish and classify them.

The gray thresholding technique used in image analysis software is not appropriate for this kind of image, as it is based on the gray level distribution of pixels. It works well with clearly defined phases that form distinct peaks on the thresholding graph.

Clemex Vision PE now has a way of processing images of various martensitic structures which does not depend on gray level thresholding. This breakthrough was accomplished after months of work on hundreds of images from industry partners.