International Journal of Pattern Recognition and Artificial Intelligence · 1992 · 106 citations · 0 references
ComputingComputer ScienceMathematicsAlgorithmsMachine LearningOptimizationDimensionality ReductionOptimization For Machine LearningOptimization TheoryPattern RecognitionLinear Discriminant Analysis
This paper presents a new method for computing the discriminant vectors of the Foley–Sammon optimal set. First, an equivalent criterion is presented to replace the Fisher criterion; then, the problem of computing the discriminant vectors in R n is transformed into the maximum problem in a subspace. Several theorems relating to the method are also presented. Experimental results show that the present method is superior to the positive pseudoinverse method, and the perturbation method in terms of correct classification rate.