COLOR MANAGEMENT EXPERIMENTS USING ADAPTIVE NEIGHBORHOODS FOR LOCAL REGRESSION 1 Color Management Experiments using Adaptive Neighborhoods for Local Regression

We built 3-D and 1-D look up tables (LUTs) to transform a user’s desired device-independent colors (CIELab) to the device-dependent color space (RGB). We considered experimental adaptive neighborhood and estimation methods for building the 3-D and 1-D LUTs. Methods of finding neighborhoods include: smallest enclosing neighborhood (SEN), smallest enclosing inclusive neighborhood (SENR), natural neighbors neighborhood (NN), natural neighbors inclusive neighborhood (NNR), and 15-nearest neighbors. The estimation techniques investigated were: local linear regression, ridge regression, and linear interpolation with maximum entropy (LIME) weighted regression. Three printers were tested using combinations of the five neighborhood definitions (SEN, SENR, NN, NNR, and 15-nearest neighbors) and three regression techniques (local linear regression, ridge regression, and LIME weighted regression).