Diploma thesis

Detection of Patterns on Micrographs of Steel


For certain high quality steel products it is necessary to remelt the raw material in an continuous process, while simultaneously cooling down the liquid steel with well controlled parameters, all protected under a cover of slag. A significant feature for the quality of the steel is the setting time during the remelting process. Based on the setting time different patterns can be observed on the prepared micrographs of probes from the remelted steel blocks.


The topic of this thesis is the detection of different setting areas on a steel probe based on locally derived image patterns. In areas of equilibrium condition the geometric arrangement of steel patterns is constant to a great extent. In areas with nonequilibrium setting a continuous changing of the patterns can be observed. This can especially be noticed in the boundary regions of the remelted steel blocks. The main tasks of the thesis are the

  • Segmentation of equilibrium and nonequilibrium setting areas.
  • Derivation of the transition area between equilibrium and nonequilibrium setting areas.
  • Definition of rules for the recognition of the transition areas based on pattern recognition.

The thesis will be conducted in the scope of the COMET-project Vision+ - Integrating visual information with independent knowledge (http://www.comet-visionplus.at).

Required Skills

C/C++, Texture Analysis, Pattern Recognition




this mastertheses at JOANNEUM RESEARCH DIGITAL is scheduled for approx. 6 month.


JOANNEUM RESEARCH offers interested students cooperation with all Austria but also European or non-European educational institutions and is willing to assist you looking for a supervisor.