Accession Number : AD0690328

Title :   A CLASS OF UPPER BOUNDS ON PROBABILITY OF ERROR FOR MULTI-HYPOTHESES PATTERN RECOGNITION.

Descriptive Note : Technical memo.,

Corporate Author : TEXAS UNIV AUSTIN ELECTRONICS RESEARCH CENTER

Personal Author(s) : Lainiotis,D. G.

Report Date : 22 APR 1969

Pagination or Media Count : 11

Abstract : A class of upper bounds on the probability of error for the general multi-hypotheses pattern recognition problem is obtained. In particular, an upper bound in the class is shown to be a linear functional of the pairwise Bhattacharya coefficients. Evaluation of the bounds requires knowledge of a priori probabilities and of the hypothesis-conditional probability density functions. A further bound is obtained that is independent of a priori probabilities. For the case of unknown a priori probabilities and conditional probability densities, an estimate of the latter upper bound is derived using a sequence of classified samples and Kernel functions to destimate the unknown densities. (Author)

Descriptors :   (*PATTERN RECOGNITION, INFORMATION THEORY), PROBABILITY DENSITY FUNCTIONS, DETECTION, ERRORS, THEOREMS

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE