Integration of an on-line handwriting recognition system in a smart phone device

Abstract : This paper presents the evolving of our academic development to a technology driven application: the integration of an unconstraint cursive on-line handwritten character recognition system into a smart phone device. The ultimate goal of this work is to implement an accuracy handwriting recognizer into mobile devices with limited computing and memory resources. A hierarchical fuzzy modeling is used to obtain a compact and robust knowledge representation and the decision process is based on an adapted fuzzy inference system to reduce computing without decreasing the performances. We describe in this paper the basic architecture of the recognition system called " ResifCar " , its practical adaptation to the mobile device constraints and the recognition rates both on cursive isolated letters (91.9%) and on isolated digits (92.3%) in a writer independent context based on 100 different writers.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [7 references]  Display  Hide  Download

https://hal.inria.fr/hal-01576053
Contributor : Eric Anquetil <>
Submitted on : Tuesday, August 22, 2017 - 2:59:53 PM
Last modification on : Friday, November 16, 2018 - 1:29:22 AM

File

ResifICPR2002Confi.pdf
Files produced by the author(s)

Identifiers

Citation

E Anquetil, H Bouchereau. Integration of an on-line handwriting recognition system in a smart phone device. International Conference on Pattern Recognition, Aug 2002, Quebec, Canada. pp.192 - 195, ⟨10.1109/ICPR.2002.1047827⟩. ⟨hal-01576053⟩

Share

Metrics

Record views

206

Files downloads

55