In this study, the problem of updating a printer characterization in response to systematic changes in print-device characteristics is addressed with two distinct approaches: the creation of corrective models used in conjunction with an existing device model, and the re-evaluation of regression-model parameters using an augmented characterization data set. Several types of corrective models are evaluated, including polynomial models and neuralnetwork models. A significant reduction in error was realized by incorporating these techniques into the color-management program NeuralColor. The most successful of these methods was a quadratic polynomial correction model, which removed 90% of the error introduced by a change of paper stock, and all of the error introduced by a change in toner cartridge. A general conclusion is that simple corrective models exhibiting global control are preferred over more complex models which may introduce local errors.
David Littlewood, Ganesh Subbarayan, "Maintaining an Accurate Printer Characterization" in Proc. IS&T 12th Color and Imaging Conf., 2004, pp 203 - 210, https://doi.org/10.2352/CIC.2004.12.1.art00037