On multiple classifier systems for pattern recognition

2 January 2003

conference paper
Published by Institute of Electrical and Electronics Engineers (IEEE)

p. 84-87
https://doi.org/10.1109/icpr.1992.201727

Abstract

Difficult pattern recognition problems involving large class sets and noisy input can be solved by a multiple classifier system, which allows simultaneous use of arbitrary feature descriptors and classification procedures. Independent decisions by each classifier can be combined by methods of the highest rank, Borda count, and logistic regression, resulting in substantial improvement in overall correctness

Keywords

LOGISTIC REGRESSION
PATTERN RECOGNITION
ARBITRARY FEATURE DESCRIPTORS
BORDA COUNT
IMAGE RECOGNITION
MULTIPLE CLASSIFIER SYSTEMS
HIGHEST RANK METHOD

This publication has 1 reference indexed in Scilit:

Graphical Methods for Assessing Logistic Regression Models
Journal of the American Statistical Association, 1984