作者: Fabíola Manhas Verbi Pereira , Maria Izabel Maretti Silveira Bueno
DOI: 10.1016/J.ACA.2007.02.009
关键词: Histogram 、 Chemometrics 、 Artificial intelligence 、 Image evaluation 、 Quality (business) 、 Gray color 、 Principal component analysis 、 Scanner 、 Chemistry 、 Pattern recognition 、 Hierarchical clustering
摘要: In this study a complementary analytical methodology for quality of paints evaluation was developed. Four different primers applied to steel substrates and submitted accelerated laboratory outdoor exposure tests were taken into account. After this, digitalized images obtained from these samples using conventional scanner. The converted in gray color scale histograms, the resulting data organized matrix form analyzed with help principal component analysis (PCA) hierarchical cluster (HCA). It possible identify best performance avoiding subjective interpretation.