Dithered quantization using neighborhood mask array to approximate interpolate

Abstract

Methods and image forming systems for approximating the value of a function given specified values of input data using a sparse lookup table. Individual samples are quantized and rounded up or down to an adjacent lattice point of the lookup table. Rather than performing multiple lookup table accesses, which are required using conventional linear interpolation, the disclosed data processing techniques require as few as one lookup table access per sample. The quantized samples are obtained by truncating one or more least significant bits, designated as masked bits, such that the most significant, or index bits, remain. For each sample, the value of an individual one of the masked bits is examined by comparing it with a corresponding entry in a mask array to determine whether the index bits are to be incremented prior to being used as an index to the lookup table. The mask array defines a dithering process whereby different masked bits are examined for different samples, resulting in dithered quantized index bits for the samples, that when used to access the lookup table, yield an average result over a neighborhood of samples that approximates the result that could be obtained using linear interpolation.