CHARACTERIZING A SURFACE COMPRISING A CURED COAT

A computer-implemented training method and system is disclosed for training a classification model for characterizing a surface comprising a cured coat. Training input measurements (TIM) based on spectroscopy measurements (ME) of training surfaces (TSU) comprising a cured coat are received and labelled in accordance with predefined surface characteristic classes (SCC) and used to train the classification model (CM). A computer-implemented classification method and system is disclosed for characterizing a surface comprising a cured coat based on the trained classification model (CM) and a spectroscopy measurement on the surface comprising a cured coat. Uses are disclosed to identify, for a surface comprising a cured coat. The surface characteristic classes (SCC) comprise one one or more classes selected from a group of binder system classes, a group of coat manufacturer classes, a group of coating product classes or a combination thereof.