An input panel and recognition engine for on-line handwritten text recognition

Authors:
Rafael Ramos-Garijo;Sergio Martín;Andrés Marzal;Federico Prat;Juan Miguel Vilar;David Llorens
Affiliations:
Departament de Llenguatges i Sistemes Informàtics, Universitat Jaume I de Castelló;Departament de Llenguatges i Sistemes Informàtics, Universitat Jaume I de Castelló;Departament de Llenguatges i Sistemes Informàtics, Universitat Jaume I de Castelló;Departament de Llenguatges i Sistemes Informàtics, Universitat Jaume I de Castelló;Departament de Llenguatges i Sistemes Informàtics, Universitat Jaume I de Castelló;Departament de Llenguatges i Sistemes Informàtics, Universitat Jaume I de Castelló
Venue:
Proceedings of the 2007 conference on Artificial Intelligence Research and Development
Year:
2007

Citing 3
Cited 0

Warping the time on data streams

Data & Knowledge Engineering
Transforming strings to vector spaces using prototype selection

SSPR'06/SPR'06 Proceedings of the 2006 joint IAPR international conference on Structural, Syntactic, and Statistical Pattern Recognition
Adaptive nonlinear auto-associative modeling through manifold learning

PAKDD'05 Proceedings of the 9th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining

Quantified Score

Hi-index	0.00

Visualization

Abstract

A portable input panel and a real-time recognition engine for isolated, handwritten characters are presented. The input panel mimics the one found in standard pen-centered interfaces and the recognition engine is based on approximate Dynamic Time Warping comparisons with prototypes selected by two different fast classification procedures. The error rate obtained on the standard Pendigits task, 0.83%, is significantly lower than the error rate of other recently published techniques.