The Community for Technology Leaders
Ninth International Workshop on Frontiers in Handwriting Recognition (2004)
Kokubunji, Tokyo, Japan
Oct. 26, 2004 to Oct. 29, 2004
ISSN: 1550-5235
ISBN: 0-7695-2187-8
pp: 3-8
Seiichi Uchida , Kyushu University
Hiroto Mitoma , Kyushu University
Hiroaki Sakoe , Kyushu University
ABSTRACT
In online character recognition based on elastic matching, such as dynamic programming matching, many of mis-recognitions are often caused by overfitting, which is the phenomenon that the distance between reference pattern of an incorrect category and an input pattern is under-estimated by unnatural matching. In this paper, a new recognition technique is proposed where category-specific deformations, called eigen-deformations, are utilized to suppress those misrecognitions. Generally, matching results at overfitting are not consistent with the eigen-deformations. Thus, the overfitting can be detected and penalized by a posterior evaluation of this inconsistency. The result of a recognition experiment showed the usefulness of the proposed technique.
INDEX TERMS
null
CITATION
Seiichi Uchida, Hiroto Mitoma, Hiroaki Sakoe, "Online Character Recognition Using Eigen-Deformations", Ninth International Workshop on Frontiers in Handwriting Recognition, vol. 00, no. , pp. 3-8, 2004, doi:10.1109/IWFHR.2004.79
84 ms
(Ver )