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

Authors:
S. Impedovo;M. G. Lucchese
Affiliations:
Dipartimento di Informatica, Università degli Studi di Bari, Bari, Italy;Dipartimento di Informatica, Università degli Studi di Bari, Bari, Italy
Venue:
AIC'05 Proceedings of the 5th WSEAS International Conference on Applied Informatics and Communications
Year:
2005

Citing 5
Cited 0

Strategies in character segmentation: a survey

ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 2) - Volume 2
Evaluation of Combination Methods

ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
Bank-check Processing System: Modifications Due to the New European Currency

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Optimizing the Number of States, Training Iterations and Gaussians in an HMM-based Handwritten Word Recognizer

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Numeral Recognition by Weighting Local Decisions

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper a new version of a bank-check processing system is presented. Many important integrations are proposed in order to improve its classification accuracy. This goal is achieved by using the Computer Aided Software Engineering tools provided by the "Khoros" software framework. New algorithms, based on Hidden Markov Models, both for courtesy and legal amount recognition, are implemented and added to those previously used for image pre-processing, amounts recognition and classifier combination. A visual programming environment is used to re-assemble the bank-check processing system that can be easily modified and extended. Experimental results, using own and international databases, show the obtained improvements.