Numeral Recognition by Weighting Local Decisions

Authors:
G. Dimauro;S. Impedovo;R. Modugno;G. Pirlo
Affiliations:
-;-;-;-
Venue:
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Year:
2003

Citing 5
Cited 4

A high accuracy algorithm for recognition of handwritten numerals

Pattern Recognition
Handwritten numerical recognition based on multiple algorithms

Pattern Recognition
On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
A structural/statistical feature based vector for handwritten character recognition

Pattern Recognition Letters
Simultaneous design of membership functions and rule sets for fuzzycontrollers using genetic algorithms

IEEE Transactions on Fuzzy Systems

Fuzzy model based recognition of handwritten numerals

Pattern Recognition
Improving a bank-check processing system with new HMM-based algorithms

AIC'05 Proceedings of the 5th WSEAS International Conference on Applied Informatics and Communications
Feature Membership Functions in Voronoi-Based Zoning

AI*IA '09: Proceedings of the XIth International Conference of the Italian Association for Artificial Intelligence Reggio Emilia on Emergent Perspectives in Artificial Intelligence
Zoning methods for handwritten character recognition: A survey

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new technique to improve thecombination of classification decisions obtained fromlocal analysis of patterns. Specifically, a geneticalgorithm is used to determine the optimal weight vectorto balance the local decisions in the combination process.The experimental results, carried out in the field ofhand-written numeral recognition, demonstrate theeffectiveness of the new technique.