Synthetic Handwritten Gesture Generation Using Sigma-Lognormal Model for Evolving Handwriting Classifiers

Abstract : We show in this paper the importance of using handwriting generation in the context of online and incremental learning of a handwriting classifier. In order to obtain realistic synthetic gestures, we apply controlled deformations on the extracted sigma-lognormal parameters of the real gesture, and we then generate synthetic gestures using the modified parameters. Results show the impact of integrating these synthetic samples generation in our learning algorithm on the classification performance.
Document type :
Conference papers
Complete list of metadatas

Cited literature [4 references]  Display  Hide  Download

https://hal.inria.fr/hal-00741573
Contributor : Abdullah Almousa Almaksour <>
Submitted on : Sunday, October 14, 2012 - 12:02:18 PM
Last modification on : Thursday, February 7, 2019 - 4:49:32 PM
Long-term archiving on : Tuesday, January 15, 2013 - 3:05:10 AM

File

IGS_paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00741573, version 1

Citation

Abdullah Almaksour, Eric Anquetil, Réjean Plamondon, Christian O'Reilly. Synthetic Handwritten Gesture Generation Using Sigma-Lognormal Model for Evolving Handwriting Classifiers. 15th Biennial Conference of the International Graphonomics Society, 2011, cancun, Mexico. ⟨hal-00741573⟩

Share

Metrics

Record views

473

Files downloads

491