Explicit fuzzy modeling of shapes and positioning for handwritten Chinese character recognition

Adrien Delaye 1, * Eric Anquetil 1 Sébastien Macé 1
* Corresponding author
1 IMADOC - Interprétation et Reconnaissance d’Images et de Documents
UR1 - Université de Rennes 1, INSA Rennes - Institut National des Sciences Appliquées - Rennes, CNRS - Centre National de la Recherche Scientifique : UMR6074
Abstract : In this paper, we present a new method for on-line Chinese character recognition that relies on an explicit description of characters structure. Contrary to most of known structural approaches, this model can describe characters written in a fluent style, thanks to a flexible fuzzy modeling of shapes and positioning of their structural components (primitives and radicals). We designed a process for incremental training of the models cooperated with automatic structural labeling for minimizing the required manual task in model design. First experiments show that the method is able to recognize non-regularly written characters and has a convincing generalization ability.
Document type :
Conference papers
Complete list of metadatas

Cited literature [6 references]  Display  Hide  Download

https://hal.inria.fr/inria-00399305
Contributor : Adrien Delaye <>
Submitted on : Friday, June 26, 2009 - 10:34:49 AM
Last modification on : Thursday, February 7, 2019 - 4:50:29 PM
Long-term archiving on : Tuesday, June 15, 2010 - 6:52:41 PM

File

3725b121.pdf
Publisher files allowed on an open archive

Identifiers

Citation

Adrien Delaye, Eric Anquetil, Sébastien Macé. Explicit fuzzy modeling of shapes and positioning for handwritten Chinese character recognition. 10th Internationl Conference on Document Analysis and Recognition, Jul 2009, Barcelone, Spain. pp.1121--1125, ⟨10.1109/ICDAR.2009.141⟩. ⟨inria-00399305⟩

Share

Metrics

Record views

362

Files downloads

147