Skip to Main content Skip to Navigation
Conference papers

Online Japanese Character Recognition Using Trajectory-Based Normalization and Direction Feature Extraction

Abstract : This paper describes an online Japanese character recognition system using advanced techniques of pattern normalization and direction feature extraction. The normalization of point coordinates and the decomposition of direction elements are directly performed on online trajectory, and therefore, are computationally efficient. We compare one-dimensional and pseudo two-dimensional (pseudo 2D) normalization methods, as well as direction features from original pattern and from normalized pattern. In experiments on the TUAT HANDS databases, the pseudo 2D normalization methods yielded superior performance, while direction features from original pattern and from normalized pattern made little difference.
Complete list of metadata

https://hal.inria.fr/inria-00108303
Contributor : Ist Rennes <>
Submitted on : Friday, October 20, 2006 - 1:03:23 PM
Last modification on : Wednesday, June 3, 2020 - 9:53:53 PM
Long-term archiving on: : Tuesday, April 6, 2010 - 8:16:40 PM

Identifiers

  • HAL Id : inria-00108303, version 1
  • PRODINRA : 252104

Collections

Citation

Cheng-Lin Liu, Xiang-Dong Zhou. Online Japanese Character Recognition Using Trajectory-Based Normalization and Direction Feature Extraction. Tenth International Workshop on Frontiers in Handwriting Recognition, Université de Rennes 1, Oct 2006, La Baule (France), France. ⟨inria-00108303⟩

Share

Metrics

Record views

1440

Files downloads

1400