A new pattern clasification algorithm named a table look-up maximum likelihood method was developed. It can achieve nearest processing speed as a conventional table look-up method in spite of the identical clasification accuracy with a maximum likelihood method. Hyperellipsoids defined by the same Mahalanobis' distance associated with each categories overlap each other in multidimensional feature space. Look-up tables in the new algorithm can be considered as orthogonal projections of these set of hyperellipsoids to each feature axes. As compared with a conventional table look-up algorithm, this algorithm is more simple, and in addition can remarkably reduce core memory requirements to store the table.
Using this new algorithm, a LANDSAT MSS image and a high-altitude color infrared aerial photograph were clasified to examine processing times. The results indicated that these rocessing rates compared with the maximum likelihood method are four and seven times faster respectively.