Image evaluation with chemometric strategies for quality control of paints Original Research Article

In this study a complementary analytical methodology for quality of paints evaluation was developed. Four different primers applied to steel substrates and submitted to accelerated laboratory and outdoor exposure tests were taken into account. After this, digitalized images were obtained from these samples using a conventional scanner. The images were converted in gray color scale histograms, the resulting data were organized into a matrix form and analyzed with the help of principal component analysis (PCA) and hierarchical cluster analysis (HCA). It was possible to identify the best primers performance avoiding subjective interpretation.