RECURSIVE DIMENSIONALITY REDUCTION USING FISHERS LINEAR DISCRIMINANT

Dimensionality reduction is an important part of the pattern recogniti on process. It would be very useful to have a recursive form for dimen sionality reduction that is suitable for implementation on massive dat a sets and real-time automatic pattern recognition systems. It would a lso be beneficial to have a version where the dimensionality reduction can be updated based on new partially identified data that are obtain ed in real systems. Versions of Fisher's Linear Discriminant for dimen sionality reduction that address these problems are derived in this ar ticle. (C) 1998 Pattern Recognition Society. Published by Elsevier Sci ence Ltd. All rights reserved.