Investigation on Color Characterization Methods for 3D Printer

In this study, the third order polynomial regression (PR) and deep neural networks (DNN) were used to perform color characterization from CMYK CIELAB space, based on a dataset consisting of 2016 samples which produced using Stratasys J750 3D printer. Five output variables including CIE XYZ, logarithm CIELAB, spectra reflectance principal components compared for performance printer characterization. The 10-fold cross validation was evaluate accuracy models developed different approaches, differences calculated with D65 illuminant. addition, effect training data sizes predictive investigated. results showed that DNN method much smaller than PR method, but it is highly dependent amount data. XYZ as provided higher XYZ.