Machine Vision Schemes towards Detecting and Estimating The State Of Corrosion

Machine Vision Schemes towards Detecting and Estimating The State Of Corrosion

P. Kapsalas (National Technical University of Athens, Greece), M. Zervakis (Technical University of Crete, Greece), P. Maravelaki-Kalaitzaki (25th Ephorate of Prehistoric & Classical Antiquities, Greece), E.T. Delegou (National Technical University of Athens, Greece) and A. Moropoulou (National Technical University of Athens,Greece)
DOI: 10.4018/978-1-60960-786-9.ch004


The systematic analysis of corrosion damage on cultural heritage objects is an aspect of multidisciplinary interest. The application of computer-aided approaches in corrosion control has recently become a challenging issue. However, the majority of researches attain to estimate the decay presence by evaluating colour and texture alterations. This work is geared towards investigating non-destructive detection and quantification of stone degradation by using machine vision schemes. The contribution of the current work is 4-fold. Thus, (1) several detection schemes were developed; each handling in a different way the background in-homogeneity (2) Numerous statistical metrics were introduced to quantify corrosion damage. These metrics mainly consider the decay areas size, spatial distribution, shape and darkness. (3) The potential of several monitoring modalities in determining corrosion attributes is studied, and (4) the corroded areas’ shape features are considered in association with the cleaning and structural state that they represent.
Chapter Preview

Non-destructive analysis methodologies provide powerful tools in the fields of material science and artwork analysis. These techniques have been extensively used recently for characterizing the cleaning state and/or the structural integrity of aerospace materials. However, little work has been done in assessing corrosion damage on stonework. The intricacy of the problem stems from the specific features of corrosion phenomena i.e. influences of various pollutant factors along with the great diversity of litho-type and the corresponding variations on decay phenomenology. An early attempt to segment degraded areas on metals was performed in (Gros, Bousique & Takahashi, 1999), where decay effects are inspected by eddy currents and infrared thermography. The information gathered is subsequently fused with the use of statistical and/or probabilistic algorithms. More recent researches (Choi & Kim, 2005) approach corrosion damage on metals by introducing morphological analysis of decay patterns to aid the characterization and classification of deterioration type. A related study reported in ‎ is focused towards recognizing the various defects encountered on a cold mill strip. Several Image Processing (IP) techniques have been developed for identifying and reconstructing corrosion damage on old paintings (Pappas & Pitas, 1998). IP approaches have been also partially employed to detect decay effects on stonework. In ‎(Cardell, Yebra & Van-Grieken, 2002), back-scattered electron images obtained with scanning electron microscopy-energy dispersive X-rays analysis were used to identify and quantify salts and porosity with depth in porous media. Moreover, methods for characterizing the stone structure and detecting regions of material loss were developed in the study of Moltedo et al.(2000), while Boukouvalas et al. ‎(1998) introduced computer vision techniques for the detection and classification of mineral veins on ceramic tiles surfaces.

Complete Chapter List

Search this Book: