Intelligent feature extraction for ensemble of classifiers
Intelligent feature extraction for ensemble of classifiers
Radtke, Paulo V.W. and Sabourin, Robert and Wong, Tony
Proceedings of the International Conference on Document Analysis and Recognition, ICDAR 2005
Abstract : This paper presents a two-level approach to create ensemble of classifiers based on intelligent feature extraction and multi-objective genetic optimization. The first stage optimizes a set of representations, which is used to create classifiers. The second stage then optimizes the ensemble’s aggregated classifiers. To assess the approach’s feasibility, a set of tests with isolated handwritten digits is performed. The experimental results encourage further researches in this direction, as the optimized ensemble of classifiers out-performs the single classifier approach. © 2005 IEEE.