Impacts of verification on a numeral string recognition system

Authors:
L. S. Oliveira;R. Sabourin;F. Bortolozzi;C. Y. Suen
Affiliations:
École de Technologie Supérieure, Département de Génie de la Production Automatisée, (LIVIA) and (CENPARMI) Montreal, Quebec, Canada;École de Technologie Supérieure, Département de Génie de la Production Automatisée, (LIVIA) and (CENPARMI), Montreal, Quebec, Canada and Pontíficia Universidade Cat&# ...;Pontíficia Universidade Católica do Paraná (PUCPR), Rua Imaculada Conceição 1155, Prado Velho, 80215-901 Curitiba Pr, Brazil;Centre for Pattern Recognition and Machine Intelligence (CENPARMI), 1455 de Maisonneuve Blvd. West, Suite GM 606, Montreal, Canada H3G 1M8
Venue:
Pattern Recognition Letters - Special issue: Sibgrapi 2001
Year:
2003

Citing 5
Cited 2

Backpropagation: the basic theory

Backpropagation
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
A Two-Stage HMM-Based System for Recognizing Handwritten Numeral Strings

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
A Modular System to Recognize Numerical Amounts on Brazilian Bank Checks

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Integrated segmentation and recognition of handwritten numeralswith cascade neural network

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

Analysis of errors of handwritten digits made by a multitude of classifiers

Pattern Recognition Letters - Special issue: In memoriam Azriel Rosenfeld
Off-line cursive script recognition: current advances, comparisons and remaining problems

Artificial Intelligence Review

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we discuss the use of high-level verification on handwritten numeral strings. First of all, we introduce the concept of levels of verification and present the baseline system used to carry out the experiments. Two different strategies were developed: absolute and one-to-one verifiers. A thorough error analysis is also presented in order to identify under which conditions high-level verification is more appropriate. Experimental results are presented on NIST SD19 database.