Training Set and Filters Selection for the Efficient Use of Multispectral Acquisition Systems

The quality of the results obtained from a multispectral acquisition system can be affected by several factors, including the training set on which the system characterization model relies and the optical filters that allow acquisition in different bands of the light spectrum. In this paper, we investigate the joint effect of training set and filter selection on the results of a typical multispectral acquisition system. We evaluate two methods for training set selection and two methods for filter selection, testing all their possible combinations and selecting filter sets and training sets of decreasing numerosity in each case. We then assess the performance of the evaluated methods by comparing the corresponding estimates for the reflectances of a representative target to the values measured using a spectrophotometer.