Automated Detection of Robust Morphology Regions to Quantify Corrosion Damage & Identify its Type

This paper examines a novel approach of corrosion damage diagnosis and restoration based on image processing for quantitative and qualitative evaluation of degradation effects on stone surfaces. This methodology can be applied in situ in association with a variety of non-destructive monitoring schemes, and on images acquired from several imaging modalities, capturing from micro- to macro-scale characteristics. Corrosion regions morphology and extent is a key aspect in the quantification of corrosion and its identification. The efficacy of various cleaning interventions as well as the characteristics and the identification of corrosion are approached through parametric and non parametric statistical significance tests. Once corroded areas have been accurately detected, they are subsequently processed in order to extract some robust features indicating structural aspects of decay. The extracted features are selected to form a multivariate feature space which in turn is clustered through unsupervised clustering techniques to obtain the different types of corrosion