Areamap and Gabor filter based Vickers hardness indentation measurement

The automated measurement of Vickers hardness indentations is demanded from industry and is an interesting image processing challenge. Different algorithms already exist but to get reliable results for all Vickers indentation images is difficult to achieve due to large variance in indentation size, position and orientation as well as in specimen surface texture and illumination conditions. A new algorithm is presented in this paper which uses AreaMaps, the LogPolar space and Gabor filter cascades to perform indentation localisation and measurement. The new approach exhibits excellent indentation detection capabilities while at the same time providing highly accurate measurement results.